The document provides an overview of capital market applications of neural networks, fuzzy logic, and genetic algorithms that have been studied in academic literature. It reviews studies that use these techniques for market forecasting, trading rules, option pricing, bond ratings, and portfolio construction. For market forecasting specifically, several studies are described that use neural networks and neuro-fuzzy systems to predict stock market indexes and interest rates, finding they often outperform traditional econometric models.
New Generation Routing Protocol over Mobile Ad Hoc Wireless Networks based on...ijasuc
There is a vast amount of researched literature available on Route Finding and Link Establishment in
MANET protocols based on various concepts such as “pro-active”, “reactive”, “power awareness”,
“cross-layering” etc. Most of these techniques are rather restrictive, taking into account a few of the
several aspects that go into effective route establishment. When we look at practical implementations of
MANETs, we have to take into account various factors in totality, not in isolation. The several factors that
decide and influence the routing have to be considered as a whole in the difficult task of finding the best
solution in route finding and optimization. The inputs to the system are manifold and apparently unrelated.
Most of the parameters are imprecise or non-crisp in nature. The uncertainty and imprecision lead to think
that intelligent routing techniques are essential and important in evolving robust and dependable solutions
to route finding. The obvious method by which this can be achieved is the deployment of soft computing
techniques such as Neural Nets, Fuzzy Logic and Genetic algorithms. Neural Networks help us to solve the
complex problem of transforming the inputs to outputs without apriori knowledge of what the relationship
is between inputs and outputs. Fuzzy Logic helps us to deal with imprecise and ill-conditioned data.
Genetic Algorithms help us to select the best possible solution from the solution space in an optimal sense.
Our paper presented here below seeks to explore new horizons in this direction. The results of our
experimentation have been very satisfactory and we have achieved the goal of optimal route finding to a
large extent. There is of course considerable room for further refinements.
Artificial neural networks and its applicationHưng Đặng
Artificial neural networks (ANNs) are non-linear data driven approaches that can identify patterns in complex data. ANNs imitate the human brain in learning from examples rather than being explicitly programmed. There are various types of ANN architectures, but feedforward and recurrent networks are most common. ANNs have been successfully applied to problems in diverse domains, including classification, prediction, and modeling where relationships are unknown. Developing an effective ANN model requires selecting variables, dividing data into training/testing/validation sets, determining network architecture, evaluating performance, and training the network through iterative adjustment of weights.
The document proposes a new approach to compare stock market patterns to DNA sequences using compression techniques. Stock market data is converted to binary sequences representing increases and decreases, which are then encoded into DNA nucleotides. These nucleotide sequences are divided and matched against human genome sequences using BLAST. The analysis found certain sub-sequences of the stock market patterns matched 100% to the human genome, suggesting this approach could potentially predict stock market behavior.
Extractive Summarization with Very Deep Pretrained Language Modelgerogepatton
The document describes a study that used BERT (Bidirectional Encoder Representations from Transformers), a pretrained language model, for extractive text summarization. The researchers developed a two-phase encoder-decoder model where BERT encoded sentences from documents and classified them as included or not included in the summary. They evaluated the model on the CNN/Daily Mail corpus and found it achieved state-of-the-art results comparable to previous models based on both automatic metrics and human evaluation.
SEMI-SUPERVISED BOOTSTRAPPING APPROACH FOR NAMED ENTITY RECOGNITIONkevig
The aim of Named Entity Recognition (NER) is to identify references of named entities in unstructured documents, and to classify them into pre-defined semantic categories. NER often aids from added background knowledge in the form of gazetteers. However using such a collection does not deal with name variants and cannot resolve ambiguities associated in identifying the entities in context and associating them with predefined categories. We present a semi-supervised NER approach that starts with identifying named entities with a small set of training data. Using the identified named entities, the word and the context features are used to define the pattern. This pattern of each named entity category is used as a seed pattern to identify the named entities in the test set. Pattern scoring and tuple value score enables the generation of the new patterns to identify the named entity categories. We have evaluated the proposed system for English language with the dataset of tagged (IEER) and untagged (CoNLL 2003) named entity corpus and for Tamil language with the documents from the FIRE corpus and yield an average f-measure of 75% for both the languages.
This document discusses an integrated approach to ontology development methodology and provides a case study using a shopping mall domain. It begins by reviewing existing ontology development methodologies and identifying their pitfalls. An integrated methodology is then proposed which aims to reduce these pitfalls. The key steps in the proposed methodology are: 1) capturing motivating user scenarios or keywords, 2) generating formal/informal questions and answers from the scenarios, 3) extracting terms and constraints, and 4) building the ontology using a top-down approach. The methodology is applied to developing an ontology for a shopping mall domain to provide multilingual information to visitors.
Fuzzy Logic approach in Gene Regulatory Network. These slides are made to present in my MSc. Bioinformatics Course II Semester, Jamia Millia Islamia, New Delhi.
It is mainly based on review paper of my teacher Dr. Khalid Raza.
Raza, Khalid. (2018). Fuzzy logic-based approaches for gene regulatory network inference. https://doi.org/10.1016/j.artmed.2018.12.004
Our project is about guessing the correct missing
word in a given sentence. To find of guess the missing word
we have two main methods one of them statistical language
modeling, while the other is neural language models.
Statistical language modeling depend on the frequency of the
relation between words and here we use Markov chain. Since
neural language models uses artificial neural networks which
uses deep learning, here we use BERT which is the state of art
in language modeling provided by google.
New Generation Routing Protocol over Mobile Ad Hoc Wireless Networks based on...ijasuc
There is a vast amount of researched literature available on Route Finding and Link Establishment in
MANET protocols based on various concepts such as “pro-active”, “reactive”, “power awareness”,
“cross-layering” etc. Most of these techniques are rather restrictive, taking into account a few of the
several aspects that go into effective route establishment. When we look at practical implementations of
MANETs, we have to take into account various factors in totality, not in isolation. The several factors that
decide and influence the routing have to be considered as a whole in the difficult task of finding the best
solution in route finding and optimization. The inputs to the system are manifold and apparently unrelated.
Most of the parameters are imprecise or non-crisp in nature. The uncertainty and imprecision lead to think
that intelligent routing techniques are essential and important in evolving robust and dependable solutions
to route finding. The obvious method by which this can be achieved is the deployment of soft computing
techniques such as Neural Nets, Fuzzy Logic and Genetic algorithms. Neural Networks help us to solve the
complex problem of transforming the inputs to outputs without apriori knowledge of what the relationship
is between inputs and outputs. Fuzzy Logic helps us to deal with imprecise and ill-conditioned data.
Genetic Algorithms help us to select the best possible solution from the solution space in an optimal sense.
Our paper presented here below seeks to explore new horizons in this direction. The results of our
experimentation have been very satisfactory and we have achieved the goal of optimal route finding to a
large extent. There is of course considerable room for further refinements.
Artificial neural networks and its applicationHưng Đặng
Artificial neural networks (ANNs) are non-linear data driven approaches that can identify patterns in complex data. ANNs imitate the human brain in learning from examples rather than being explicitly programmed. There are various types of ANN architectures, but feedforward and recurrent networks are most common. ANNs have been successfully applied to problems in diverse domains, including classification, prediction, and modeling where relationships are unknown. Developing an effective ANN model requires selecting variables, dividing data into training/testing/validation sets, determining network architecture, evaluating performance, and training the network through iterative adjustment of weights.
The document proposes a new approach to compare stock market patterns to DNA sequences using compression techniques. Stock market data is converted to binary sequences representing increases and decreases, which are then encoded into DNA nucleotides. These nucleotide sequences are divided and matched against human genome sequences using BLAST. The analysis found certain sub-sequences of the stock market patterns matched 100% to the human genome, suggesting this approach could potentially predict stock market behavior.
Extractive Summarization with Very Deep Pretrained Language Modelgerogepatton
The document describes a study that used BERT (Bidirectional Encoder Representations from Transformers), a pretrained language model, for extractive text summarization. The researchers developed a two-phase encoder-decoder model where BERT encoded sentences from documents and classified them as included or not included in the summary. They evaluated the model on the CNN/Daily Mail corpus and found it achieved state-of-the-art results comparable to previous models based on both automatic metrics and human evaluation.
SEMI-SUPERVISED BOOTSTRAPPING APPROACH FOR NAMED ENTITY RECOGNITIONkevig
The aim of Named Entity Recognition (NER) is to identify references of named entities in unstructured documents, and to classify them into pre-defined semantic categories. NER often aids from added background knowledge in the form of gazetteers. However using such a collection does not deal with name variants and cannot resolve ambiguities associated in identifying the entities in context and associating them with predefined categories. We present a semi-supervised NER approach that starts with identifying named entities with a small set of training data. Using the identified named entities, the word and the context features are used to define the pattern. This pattern of each named entity category is used as a seed pattern to identify the named entities in the test set. Pattern scoring and tuple value score enables the generation of the new patterns to identify the named entity categories. We have evaluated the proposed system for English language with the dataset of tagged (IEER) and untagged (CoNLL 2003) named entity corpus and for Tamil language with the documents from the FIRE corpus and yield an average f-measure of 75% for both the languages.
This document discusses an integrated approach to ontology development methodology and provides a case study using a shopping mall domain. It begins by reviewing existing ontology development methodologies and identifying their pitfalls. An integrated methodology is then proposed which aims to reduce these pitfalls. The key steps in the proposed methodology are: 1) capturing motivating user scenarios or keywords, 2) generating formal/informal questions and answers from the scenarios, 3) extracting terms and constraints, and 4) building the ontology using a top-down approach. The methodology is applied to developing an ontology for a shopping mall domain to provide multilingual information to visitors.
Fuzzy Logic approach in Gene Regulatory Network. These slides are made to present in my MSc. Bioinformatics Course II Semester, Jamia Millia Islamia, New Delhi.
It is mainly based on review paper of my teacher Dr. Khalid Raza.
Raza, Khalid. (2018). Fuzzy logic-based approaches for gene regulatory network inference. https://doi.org/10.1016/j.artmed.2018.12.004
Our project is about guessing the correct missing
word in a given sentence. To find of guess the missing word
we have two main methods one of them statistical language
modeling, while the other is neural language models.
Statistical language modeling depend on the frequency of the
relation between words and here we use Markov chain. Since
neural language models uses artificial neural networks which
uses deep learning, here we use BERT which is the state of art
in language modeling provided by google.
Conceptual similarity measurement algorithm for domain specific ontology[Zac Darcy
This paper presents the similarity measurement algorithm for domain specific terms collected in the
ontology based data integration system. This similarity measurement algorithm can be used in ontology
mapping and query service of
ontology based data integration sy
stem. In this paper, we focus
o
n the web
query service to apply
this proposed algorithm
. Concepts similarity is important for web query service
because the words in user input query are not
same wholly with the concepts in
ontology. So, we need to
extract the possible concepts that are match or related to the input words with the help of machine readable
dictionary WordNet. Sometimes, we use the generated mapping rules in query generation procedure for
some words that canno
t be
confirmed the similarity of these words
by WordNet. We prove the effect
of this
algorithm with two degree semantic result of web minin
g by generating
the concepts results obtained form
the input query
This document discusses several approaches for embedding knowledge bases and relations into continuous vector spaces using neural networks. It first describes earlier models like semantic embedding which used simple scoring functions based on distance between entity embeddings. More advanced models like semantic matching energy and neural tensor networks learn separate relation embeddings and use them to calculate entity interactions. The document also discusses applications of these embeddings for tasks like link prediction, question answering and knowledge base expansion. It provides details of various models' scoring functions, training objectives and datasets used for evaluation.
This document presents a new model called EQUIRS (Explicitly Query Understanding Information Retrieval System) based on Hidden Markov Models (HMM) to improve natural language processing for text query information retrieval. The proposed EQUIRS system is compared to previous fuzzy clustering methods. Experimental results on a dataset of 900 files across 5 categories show that EQUIRS has higher accuracy than fuzzy clustering, as measured by precision, recall, F-measure, though it has longer training and searching times. The document concludes that EQUIRS is an effective approach for information retrieval based on HMM.
This document discusses several approaches for embedding knowledge bases and relations into continuous vector spaces using neural networks. It first describes earlier models like semantic embedding and semantic matching energy which used single hidden layers. It then explains more complex models like neural tensor networks that use tensors to model relations. The document also discusses applications of these embeddings for tasks like link prediction, question answering, and knowledge base expansion. It provides details on model formulations, scoring functions, training objectives, and datasets used for evaluation.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
The project re-implements the architecture of the paper Reasoning with Neural Tensor Networks for Knowledge Base Completion in Torch framework, achieving similar accuracy results with an elegant implementation in a modern language.
Below are some links for further details:
https://github.com/agarwal-shubham/Reasoning-Over-Knowledge-Base
http://darsh510.github.io/IREPROJ/
Sentiment Analysis In Myanmar Language Using Convolutional Lstm Neural Networkkevig
In recent years, there has been an increasing use of social media among people in Myanmar and writing
review on social media pages about the product, movie, and trip are also popular among people. Moreover,
most of the people are going to find the review pages about the product they want to buy before deciding
whether they should buy it or not. Extracting and receiving useful reviews over interesting products is very
important and time consuming for people. Sentiment analysis is one of the important processes for extracting
useful reviews of the products. In this paper, the Convolutional LSTM neural network architecture is
proposed to analyse the sentiment classification of cosmetic reviews written in Myanmar Language. The
paper also intends to build the cosmetic reviews dataset for deep learning and sentiment lexicon in Myanmar
Language.
Chunking means splitting the sentences into tokens and then grouping them in a meaningful way. When it comes to high-performance chunking systems, transformer models have proved to be the state of the art benchmarks. To perform chunking as a task it requires a large-scale high quality annotated corpus where each token is attached with a particular tag similar as that of Named Entity Recognition Tasks. Later these tags are used in conjunction with pointer frameworks to find the final chunk. To solve this for a specific domain problem, it becomes a highly costly affair in terms of time and resources to manually annotate and produce a large-high-quality training set. When the domain is specific and diverse, then cold starting becomes even more difficult because of the expected large number of manually annotated queries to cover all aspects. To overcome the problem, we applied a grammar-based text generation mechanism where instead of annotating a sentence we annotate using grammar templates. We defined various templates corresponding to different grammar rules. To create a sentence we used these templates along with the rules where symbol or terminal values were chosen from the domain data catalog. It helped us to create a large number of annotated queries. These annotated queries were used for training the machine learning model using an ensemble transformer-based deep neural network model [24.] We found that grammar-based annotation was useful to solve domain-based chunks in input query sentences without any manual annotation where it was found to achieve a classification F1 score of 96.97% in classifying the tokens for the out of template queries.
Taxonomy extraction from automotive natural language requirements using unsup...ijnlc
In this paper we present a novel approach to semi-automatically learn concept hierarchies from natural
language requirements of the automotive industry. The approach is based on the distributional hypothesis
and the special characteristics of domain-specific German compounds. We extract taxonomies by using
clustering techniques in combination with general thesauri. Such a taxonomy can be used to support
requirements engineering in early stages by providing a common system understanding and an agreedupon
terminology. This work is part of an ontology-driven requirements engineering process, which builds
on top of the taxonomy. Evaluation shows that this taxonomy extraction approach outperforms common
hierarchical clustering techniques.
Concept hierarchy is the backbone of ontology, and the concept hierarchy acquisition has been a hot topic in the field of ontology learning. this paper proposes a hyponymy extraction method of domain ontology concept based on cascaded conditional random field(CCRFs) and hierarchy clustering. It takes free text as extracting object, adopts CCRFs identifying the domain concepts. First the low layer of CCRFs is used to identify simple domain concept, then the results are sent to the high layer, in which the nesting concepts are recognized. Next we adopt hierarchy clustering to identify the hyponymy relation between domain ontology concepts. The experimental results demonstrate the proposed method is efficient.
This document summarizes a semi-supervised clustering approach for classifying P300 signals for brain-computer interface (BCI) speller systems. It involves using k-means clustering on wavelet features extracted from EEG data, with some data points labeled to initialize the clusters. An ensemble of support vector machines is then trained on the clustered data points to classify new unlabeled P300 signals. The document outlines the P300 speller paradigm used to collect the EEG data, pre-processing steps like filtering and wavelet transformation, the seeded k-means semi-supervised clustering method, and using an ensemble SVM classifier trained on the clustered data for classification.
Take-Home Exam Questions on Brain and Computation'butest
This document provides instructions for a take-home exam on the topic of "Brain and Computation". It outlines 5 questions to be answered in 2 pages or less each, for a total of no more than 10 pages. The questions address various computational models of neurons and neuronal networks, mechanisms of synaptic plasticity and learning, and feed-forward neural networks. Students are asked to use equations where applicable and form their own responses rather than copying directly from the textbook. The exam is due by email and hard copy one week after it is distributed.
Trajectory Data Fuzzy Modeling : Ambulances Management Use Caseijdms
Data captured through mobile devices and sensors represent valuable information for organizations. This
collected information comes in huge volume and usually carry uncertain data. Due to this quality issue
difficulties occur in analyzing the trajectory data warehouse. Moreover, the interpretation of the analysis
can vary depending on the background of the user and this will make it difficult to fulfill the analytical
needs of an enterprise. In this paper, we will show the benefits of fuzzy logic in solving the challenges
related to mobility data by integrating fuzzy concepts into the conceptual and the logical model. We use the
ambulance management use case to illustrate our contributions.
The document discusses a novel domain ontology discovery method that exploits contextual information from knowledge sources to construct domain ontologies. It involves parsing text, identifying lexical patterns, extracting linguistic patterns, performing statistical token analysis using mutual information, and developing a taxonomy of domain concepts. The proposed method aims to assist in building domain ontologies more quickly and accurately compared to existing methods.
Predicting Forced Population Displacement Using News ArticlesJaresJournal
The world has witnessed mass forced population displacement across the globe. Population displacement has various indications, with different social and policy consequences. Mitigation of the humanitarian crisis requires tracking and predicting the population movements to
allocate the necessary resources and inform the policymakers. The set of events that triggers population movements can be traced in the news articles. In this paper, we propose the Population
Displacement-Signal Extraction Framework (PD-SEF) to explore a large news corpus and extract
the signals of forced population displacement. PD-SEF measures and evaluates violence signals,
which is a critical factor of forced displacement from it. Following signal extraction, we propose a
displacement prediction model based on extracted violence scores. Experimental results indicate
the effectiveness of our framework in extracting high quality violence scores and building accurate
prediction models.
The document discusses various network topologies including physical and logical topologies. It describes key topologies such as bus, star, ring, mesh, tree, hybrid, and daisy chain. Physical topology refers to the physical layout and connections of a network, while logical topology refers to the logical path data takes between nodes regardless of physical design. There are eight basic network topologies that are described in detail.
A DOMAIN INDEPENDENT APPROACH FOR ONTOLOGY SEMANTIC ENRICHMENTcscpconf
Ontology automatic enrichment consists of adding automatically new concepts and/or new relations to an initial ontology built manually using a basic domain knowledge. In a concrete manner, enrichment is firstly, extracting concepts and relations from textual sources then putting them in their right emplacements in the initial ontology. However, the main issue in that process is how to preserve the coherence of the ontology after this operation. For this purpose, we consider the semantic aspect in the enrichment process by using similarity techniques between terms. Contrarily to other approaches, our approach is domain independent and the enrichment process is based on a semantic analysis. Another advantage of our approach is that it takes into account the two types of relations, taxonomic and non taxonomic
ones.
This document summarizes a student project that analyzed speech data to predict schizophrenia using machine learning algorithms. The students collected speech data from schizophrenic and healthy individuals over two days. They tested logistic regression, naive Bayes, random forest, decision tree, and OneR algorithms on the data. Logistic regression performed best, accurately predicting schizophrenia from emotions data over 80% of the time. The small dataset size was a challenge, and future work could involve implementing support vector machines and obtaining a larger dataset.
La Unión Europea ha acordado un paquete de sanciones contra Rusia por su invasión de Ucrania. Las sanciones incluyen restricciones a las importaciones de productos rusos de alta tecnología y a las exportaciones de bienes de lujo a Rusia. Además, se congelarán los activos de varios oligarcas rusos y se prohibirá el acceso de los bancos rusos a los mercados financieros de la UE.
A empresa de tecnologia anunciou um novo smartphone com câmera aprimorada, tela maior e bateria de longa duração por um preço acessível. O dispositivo tem como objetivo atrair mais consumidores em mercados emergentes com suas especificações equilibradas e preço baixo. Analistas esperam que as melhorias e o preço baixo impulsionem as vendas do novo aparelho.
Conceptual similarity measurement algorithm for domain specific ontology[Zac Darcy
This paper presents the similarity measurement algorithm for domain specific terms collected in the
ontology based data integration system. This similarity measurement algorithm can be used in ontology
mapping and query service of
ontology based data integration sy
stem. In this paper, we focus
o
n the web
query service to apply
this proposed algorithm
. Concepts similarity is important for web query service
because the words in user input query are not
same wholly with the concepts in
ontology. So, we need to
extract the possible concepts that are match or related to the input words with the help of machine readable
dictionary WordNet. Sometimes, we use the generated mapping rules in query generation procedure for
some words that canno
t be
confirmed the similarity of these words
by WordNet. We prove the effect
of this
algorithm with two degree semantic result of web minin
g by generating
the concepts results obtained form
the input query
This document discusses several approaches for embedding knowledge bases and relations into continuous vector spaces using neural networks. It first describes earlier models like semantic embedding which used simple scoring functions based on distance between entity embeddings. More advanced models like semantic matching energy and neural tensor networks learn separate relation embeddings and use them to calculate entity interactions. The document also discusses applications of these embeddings for tasks like link prediction, question answering and knowledge base expansion. It provides details of various models' scoring functions, training objectives and datasets used for evaluation.
This document presents a new model called EQUIRS (Explicitly Query Understanding Information Retrieval System) based on Hidden Markov Models (HMM) to improve natural language processing for text query information retrieval. The proposed EQUIRS system is compared to previous fuzzy clustering methods. Experimental results on a dataset of 900 files across 5 categories show that EQUIRS has higher accuracy than fuzzy clustering, as measured by precision, recall, F-measure, though it has longer training and searching times. The document concludes that EQUIRS is an effective approach for information retrieval based on HMM.
This document discusses several approaches for embedding knowledge bases and relations into continuous vector spaces using neural networks. It first describes earlier models like semantic embedding and semantic matching energy which used single hidden layers. It then explains more complex models like neural tensor networks that use tensors to model relations. The document also discusses applications of these embeddings for tasks like link prediction, question answering, and knowledge base expansion. It provides details on model formulations, scoring functions, training objectives, and datasets used for evaluation.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
The project re-implements the architecture of the paper Reasoning with Neural Tensor Networks for Knowledge Base Completion in Torch framework, achieving similar accuracy results with an elegant implementation in a modern language.
Below are some links for further details:
https://github.com/agarwal-shubham/Reasoning-Over-Knowledge-Base
http://darsh510.github.io/IREPROJ/
Sentiment Analysis In Myanmar Language Using Convolutional Lstm Neural Networkkevig
In recent years, there has been an increasing use of social media among people in Myanmar and writing
review on social media pages about the product, movie, and trip are also popular among people. Moreover,
most of the people are going to find the review pages about the product they want to buy before deciding
whether they should buy it or not. Extracting and receiving useful reviews over interesting products is very
important and time consuming for people. Sentiment analysis is one of the important processes for extracting
useful reviews of the products. In this paper, the Convolutional LSTM neural network architecture is
proposed to analyse the sentiment classification of cosmetic reviews written in Myanmar Language. The
paper also intends to build the cosmetic reviews dataset for deep learning and sentiment lexicon in Myanmar
Language.
Chunking means splitting the sentences into tokens and then grouping them in a meaningful way. When it comes to high-performance chunking systems, transformer models have proved to be the state of the art benchmarks. To perform chunking as a task it requires a large-scale high quality annotated corpus where each token is attached with a particular tag similar as that of Named Entity Recognition Tasks. Later these tags are used in conjunction with pointer frameworks to find the final chunk. To solve this for a specific domain problem, it becomes a highly costly affair in terms of time and resources to manually annotate and produce a large-high-quality training set. When the domain is specific and diverse, then cold starting becomes even more difficult because of the expected large number of manually annotated queries to cover all aspects. To overcome the problem, we applied a grammar-based text generation mechanism where instead of annotating a sentence we annotate using grammar templates. We defined various templates corresponding to different grammar rules. To create a sentence we used these templates along with the rules where symbol or terminal values were chosen from the domain data catalog. It helped us to create a large number of annotated queries. These annotated queries were used for training the machine learning model using an ensemble transformer-based deep neural network model [24.] We found that grammar-based annotation was useful to solve domain-based chunks in input query sentences without any manual annotation where it was found to achieve a classification F1 score of 96.97% in classifying the tokens for the out of template queries.
Taxonomy extraction from automotive natural language requirements using unsup...ijnlc
In this paper we present a novel approach to semi-automatically learn concept hierarchies from natural
language requirements of the automotive industry. The approach is based on the distributional hypothesis
and the special characteristics of domain-specific German compounds. We extract taxonomies by using
clustering techniques in combination with general thesauri. Such a taxonomy can be used to support
requirements engineering in early stages by providing a common system understanding and an agreedupon
terminology. This work is part of an ontology-driven requirements engineering process, which builds
on top of the taxonomy. Evaluation shows that this taxonomy extraction approach outperforms common
hierarchical clustering techniques.
Concept hierarchy is the backbone of ontology, and the concept hierarchy acquisition has been a hot topic in the field of ontology learning. this paper proposes a hyponymy extraction method of domain ontology concept based on cascaded conditional random field(CCRFs) and hierarchy clustering. It takes free text as extracting object, adopts CCRFs identifying the domain concepts. First the low layer of CCRFs is used to identify simple domain concept, then the results are sent to the high layer, in which the nesting concepts are recognized. Next we adopt hierarchy clustering to identify the hyponymy relation between domain ontology concepts. The experimental results demonstrate the proposed method is efficient.
This document summarizes a semi-supervised clustering approach for classifying P300 signals for brain-computer interface (BCI) speller systems. It involves using k-means clustering on wavelet features extracted from EEG data, with some data points labeled to initialize the clusters. An ensemble of support vector machines is then trained on the clustered data points to classify new unlabeled P300 signals. The document outlines the P300 speller paradigm used to collect the EEG data, pre-processing steps like filtering and wavelet transformation, the seeded k-means semi-supervised clustering method, and using an ensemble SVM classifier trained on the clustered data for classification.
Take-Home Exam Questions on Brain and Computation'butest
This document provides instructions for a take-home exam on the topic of "Brain and Computation". It outlines 5 questions to be answered in 2 pages or less each, for a total of no more than 10 pages. The questions address various computational models of neurons and neuronal networks, mechanisms of synaptic plasticity and learning, and feed-forward neural networks. Students are asked to use equations where applicable and form their own responses rather than copying directly from the textbook. The exam is due by email and hard copy one week after it is distributed.
Trajectory Data Fuzzy Modeling : Ambulances Management Use Caseijdms
Data captured through mobile devices and sensors represent valuable information for organizations. This
collected information comes in huge volume and usually carry uncertain data. Due to this quality issue
difficulties occur in analyzing the trajectory data warehouse. Moreover, the interpretation of the analysis
can vary depending on the background of the user and this will make it difficult to fulfill the analytical
needs of an enterprise. In this paper, we will show the benefits of fuzzy logic in solving the challenges
related to mobility data by integrating fuzzy concepts into the conceptual and the logical model. We use the
ambulance management use case to illustrate our contributions.
The document discusses a novel domain ontology discovery method that exploits contextual information from knowledge sources to construct domain ontologies. It involves parsing text, identifying lexical patterns, extracting linguistic patterns, performing statistical token analysis using mutual information, and developing a taxonomy of domain concepts. The proposed method aims to assist in building domain ontologies more quickly and accurately compared to existing methods.
Predicting Forced Population Displacement Using News ArticlesJaresJournal
The world has witnessed mass forced population displacement across the globe. Population displacement has various indications, with different social and policy consequences. Mitigation of the humanitarian crisis requires tracking and predicting the population movements to
allocate the necessary resources and inform the policymakers. The set of events that triggers population movements can be traced in the news articles. In this paper, we propose the Population
Displacement-Signal Extraction Framework (PD-SEF) to explore a large news corpus and extract
the signals of forced population displacement. PD-SEF measures and evaluates violence signals,
which is a critical factor of forced displacement from it. Following signal extraction, we propose a
displacement prediction model based on extracted violence scores. Experimental results indicate
the effectiveness of our framework in extracting high quality violence scores and building accurate
prediction models.
The document discusses various network topologies including physical and logical topologies. It describes key topologies such as bus, star, ring, mesh, tree, hybrid, and daisy chain. Physical topology refers to the physical layout and connections of a network, while logical topology refers to the logical path data takes between nodes regardless of physical design. There are eight basic network topologies that are described in detail.
A DOMAIN INDEPENDENT APPROACH FOR ONTOLOGY SEMANTIC ENRICHMENTcscpconf
Ontology automatic enrichment consists of adding automatically new concepts and/or new relations to an initial ontology built manually using a basic domain knowledge. In a concrete manner, enrichment is firstly, extracting concepts and relations from textual sources then putting them in their right emplacements in the initial ontology. However, the main issue in that process is how to preserve the coherence of the ontology after this operation. For this purpose, we consider the semantic aspect in the enrichment process by using similarity techniques between terms. Contrarily to other approaches, our approach is domain independent and the enrichment process is based on a semantic analysis. Another advantage of our approach is that it takes into account the two types of relations, taxonomic and non taxonomic
ones.
This document summarizes a student project that analyzed speech data to predict schizophrenia using machine learning algorithms. The students collected speech data from schizophrenic and healthy individuals over two days. They tested logistic regression, naive Bayes, random forest, decision tree, and OneR algorithms on the data. Logistic regression performed best, accurately predicting schizophrenia from emotions data over 80% of the time. The small dataset size was a challenge, and future work could involve implementing support vector machines and obtaining a larger dataset.
La Unión Europea ha acordado un paquete de sanciones contra Rusia por su invasión de Ucrania. Las sanciones incluyen restricciones a las importaciones de productos rusos de alta tecnología y a las exportaciones de bienes de lujo a Rusia. Además, se congelarán los activos de varios oligarcas rusos y se prohibirá el acceso de los bancos rusos a los mercados financieros de la UE.
A empresa de tecnologia anunciou um novo smartphone com câmera aprimorada, tela maior e bateria de longa duração por um preço acessível. O dispositivo tem como objetivo atrair mais consumidores em mercados emergentes com suas especificações equilibradas e preço baixo. Analistas esperam que as melhorias e o preço baixo impulsionem as vendas do novo aparelho.
This document summarizes the results of a survey conducted by the IACC Emerging Trends Committee and Development Counsellors International on generational preferences in meeting location selection. The survey received 94 responses from meeting planners across different generations. Key findings include that location, meeting space flexibility, and cost were the most important factors for all generations. Younger generations placed more importance on amenities, activities, and technology compared to older generations. The top reasons for declining a facility were cost, inadequate meeting space, and location.
This document summarizes a study that examines the information content of different types of short sales on the New York Stock Exchange. The study uses a large dataset of short sale orders from the NYSE that identifies the account type (individual, institutional, etc.) initiating each short sale. The study finds that institutional short sales, especially large non-program trades, contain the most private information and are the best at predicting future stock underperformance. Stocks heavily shorted by institutions underperform lightly shorted peers by over 1.3% in the following month. In contrast, small short sales and those by individuals contain less private information and stocks tend to rise after such shorting activity.
New Generation Routing Protocol over Mobile Ad Hoc Wireless Networks based on...ijasuc
There is a vast amount of researched literature available on Route Finding and Link Establishment in
MANET protocols based on various concepts such as “pro-active”, “reactive”, “power awareness”,
“cross-layering” etc. Most of these techniques are rather restrictive, taking into account a few of the
several aspects that go into effective route establishment. When we look at practical implementations of
MANETs, we have to take into account various factors in totality, not in isolation. The several factors that
decide and influence the routing have to be considered as a whole in the difficult task of finding the best
solution in route finding and optimization. The inputs to the system are manifold and apparently unrelated.
Most of the parameters are imprecise or non-crisp in nature. The uncertainty and imprecision lead to think
that intelligent routing techniques are essential and important in evolving robust and dependable solutions
to route finding. The obvious method by which this can be achieved is the deployment of soft computing
techniques such as Neural Nets, Fuzzy Logic and Genetic algorithms. Neural Networks help us to solve the
complex problem of transforming the inputs to outputs without apriori knowledge of what the relationship
is between inputs and outputs. Fuzzy Logic helps us to deal with imprecise and ill-conditioned data.
Genetic Algorithms help us to select the best possible solution from the solution space in an optimal sense.
Our paper presented here below seeks to explore new horizons in this direction. The results of our
experimentation have been very satisfactory and we have achieved the goal of optimal route finding to a
large extent. There is of course considerable room for further refinements.
This document discusses using an artificial neural network to forecast stock price indices in a stock exchange. It begins with an abstract that notes ANNs have been used successfully for non-linear business forecasting. The paper then aims to present a better prediction model for stock indices using neural network techniques in the Indian context. It reviews single and multilayer networks, and the backpropagation method for training multilayer networks.
This document proposes a new method for extracting rules from trained multilayer artificial neural networks that can represent rules in both "if-then" and "M of N" formats. The method extracts an intermediate structure called a "generator list" from which both types of rules can be derived. This provides a more generic representation than existing methods that can only output one rule format. The generator list approach avoids preprocessing steps used in other methods that can modify the original network. It uses heuristics to prune the search space when extracting the generator list to address the computational complexity involved.
Efficient Forecasting of Exchange rates with Recurrent FLANNIOSR Journals
The document proposes a Functional Link Artificial Recurrent Neural Network (FLARNN) model for forecasting foreign exchange rates between currencies like the US dollar, Indian rupee, British pound, and Japanese yen. It compares the performance of the FLARNN model to existing neural network models like LMS and FLANN. The FLARNN uses functional expansion and recurrent connections to more accurately predict exchange rates up to 60 days in the future based on historical data. Experimental results show the FLARNN model consistently outperforms the other methods according to error convergence and Mean Average Percentage Error.
An Artificial Intelligence Approach to Ultra High Frequency Path Loss Modelli...ijtsrd
This study proposes Artificial Intelligence AI based path loss prediction models for the suburban areas of Abuja, Nigeria. The AI based models were created on the bases of two deep learning networks, namely the Adaptive Neuro Fuzzy Inference System ANFIS and the Generalized Radial Basis Function Neural network RBF NN . These prediction models were created, trained, validated and tested for path loss prediction using path loss data recorded at 1800MHz from multiple Base Transceiver Stations BTSs distributed across the areas under investigation. Results indicate that the ANFIS and RBF NN based models with Root Mean Squared Error RMSE values of 5.30dB and 5.31dB respectively, offer greater prediction accuracy over the widely used empirical COST 231 Hata, which has an RMSE of 8.18dB. Deme C. Abraham ""An Artificial Intelligence Approach to Ultra-High Frequency Path Loss Modelling of the Suburban Areas of Abuja, Nigeria"" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-2 , February 2020,
URL: https://www.ijtsrd.com/papers/ijtsrd30227.pdf
Paper Url : https://www.ijtsrd.com/computer-science/artificial-intelligence/30227/an-artificial-intelligence-approach-to-ultra-high-frequency-path-loss-modelling-of-the-suburban-areas-of-abuja-nigeria/deme-c-abraham
Crude Oil Price Prediction Based on Soft Computing Model: Case Study of IraqKiogyf
This paper proposes using a multi-layer perceptron neural network (MLP-NN) soft computing model to accurately predict future crude oil prices in Iraq. The performance of the MLP-NN model is compared to other neural network approaches and found to perform better, especially with limited training data and high parameter variability. The paper describes the MLP-NN model and its training process using a dataset of Iraqi crude oil prices from 1990 to 2018. Features like mutual information analysis and data normalization are used as part of the model building process.
This document discusses hybrid learning approaches for Adaptive Neuro Fuzzy Inference Systems (ANFIS). It describes the ANFIS architecture, which combines artificial neural networks and fuzzy logic. The training algorithms analyzed are Back Propagation, gradient descent, and Runge-Kutta learning. Experiments showed that ANFIS combined with Runge-Kutta learning provides better training error results than the other methods. The hybrid approach allows ANFIS to incorporate human expertise and adapt through learning input-output data.
Stock Prediction Using Artificial Neural Networksijbuiiir1
This document describes a study that uses artificial neural networks to predict stock prices. It discusses justifying the use of ANNs for stock price forecasting due to their ability to model nonlinear relationships without prior assumptions. The study develops a neural network with input layer containing stock data (e.g. price, volume), a hidden layer, and output layer to predict future closing prices. The network is trained on 70% of stock data from four companies and tested on remaining 30% to evaluate performance using error metrics.
Investigations on Hybrid Learning in ANFISIJERA Editor
Neural networks have attractiveness to several researchers due to their great closeness to the structure of the brain, their characteristics not shared by many traditional systems. An Artificial Neural Network (ANN) is a network of interconnected artificial processing elements (called neurons) that co-operate with one another in order to solve specific issues. ANNs are inspired by the structure and functional aspects of biological nervous systems. Neural networks, which recognize patterns and adopt themselves to cope with changing environments. Fuzzy inference system incorporates human knowledge and performs inferencing and decision making. The integration of these two complementary approaches together with certain derivative free optimization techniques, results in a novel discipline called Neuro Fuzzy. In Neuro fuzzy development a specific approach is called Adaptive Neuro Fuzzy Inference System (ANFIS), which has shown significant results in modeling nonlinear functions. The basic idea behind the paper is to design a system that uses a fuzzy system to represent knowledge in an interpretable manner and have the learning ability derived from a Runge-Kutta learning method (RKLM) to adjust its membership functions and parameters in order to enhance the system performance. The problem of finding appropriate membership functions and fuzzy rules is often a tiring process of trial and error. It requires users to understand the data before training, which is usually difficult to achieve when the database is relatively large. To overcome these problems, a hybrid of Back Propagation Neural network (BPN) and RKLM can combine the advantages of two systems and avoid their disadvantages.
Soft computing is a set of computational techniques that aim to mimic human-like reasoning and decision making. The main techniques are fuzzy logic, neural networks, evolutionary computing, machine learning, and probabilistic reasoning. Each technique has strengths and weaknesses, but they complement each other. When used together, soft computing techniques can solve complex problems that are difficult for traditional mathematical methods. The paper reviews these soft computing techniques and explores how they could be applied to problems in various domains.
Time Series Forecasting Using Novel Feature Extraction Algorithm and Multilay...Editor IJCATR
Time series forecasting is important because it can often provide the foundation for decision making in a large variety of fields. A tree-ensemble method, referred to as time series forest (TSF), is proposed for time series classification. The approach is based on the concept of data series envelopes and essential attributes generated by a multilayer neural network... These claims are further investigated by applying statistical tests. With the results presented in this article and results from related investigations that are considered as well, we want to support practitioners or scholars in answering the following question: Which measure should be looked at first if accuracy is the most important criterion, if an application is time-critical, or if a compromise is needed? In this paper demonstrated feature extraction by novel method can improvement in time series data forecasting process
Artificial neural networks and its applicationHưng Đặng
Artificial neural networks (ANNs) are non-linear data driven approaches that can identify patterns in complex data. ANNs imitate the human brain in learning from examples rather than being explicitly programmed. There are various types of ANN architectures, but feedforward and recurrent networks are most common. ANNs have been successfully applied to problems in diverse domains, including classification, prediction, and modeling where relationships are unknown. Developing an effective ANN model requires selecting variables, dividing data into training/testing/validation sets, determining network architecture, evaluating performance, and training the network through iterative adjustment of weights.
Survey on Artificial Neural Network Learning Technique AlgorithmsIRJET Journal
This document discusses different types of learning algorithms used in artificial neural networks. It begins with an introduction to neural networks and their ability to learn from their environment through adjustments to synaptic weights. Four main learning algorithms are then described: error correction learning, which uses algorithms like backpropagation to minimize error; memory based learning, which stores all training examples and analyzes nearby examples to classify new inputs; Hebbian learning, where connection weights are adjusted based on the activity of neurons; and competitive learning, where neurons compete to respond to inputs to become specialized feature detectors through a winner-take-all mechanism. The document provides details on how each type of learning algorithm works.
Artificial Neural Networks: Applications In ManagementIOSR Journals
With the advancement of computer and communication technology, the tools used for management decisions have undergone a gigantic change. Finding the more effective solution and tools for managerial problems is one of the most important topics in the management studies today. Artificial Neural Networks (ANNs) are one of these tools that have become a critical component for business intelligence. The purpose of this article is to describe the basic behavior of neural networks as well as the works done in application of the same in management sciences and stimulate further research interests and efforts in the identified topics.
Fuzzy modeling require two main steps which are structure identification and parameter optimization, the
first one determines the numbers of membership functions and fuzzy if-then rules, while the second
identifies a feasible set of parameters under the given structure. However, the increase of input dimension,
rule numbers will have an exponential growth and there will cause problem of “rule disaster”. In this
paper, we have applied adaptive network fuzzy inference system ANFIS for phonemes recognition. The
appropriate learning algorithm is performed on TIMIT speech database supervised type, a pre-processing
of the acoustic signal and extracting the coefficients MFCCs parameters relevant to the recognition system.
First learning of the network structure by subtractive clustering, in order to define an optimal structure and
obtain small number of rules, then learning of parameters network by hybrid learning which combine the
gradient decent and least square estimation LSE to find a feasible set of antecedents and consequents
parameters. The results obtained show the effectiveness of the method in terms of recognition rate and
number of fuzzy rules generated.
NETWORK LEARNING AND TRAINING OF A CASCADED LINK-BASED FEED FORWARD NEURAL NE...ijaia
Presently, considering the technological advancement of our modern world, we are in dire need for a system that can learn new concepts and give decisions on its own. Hence the Artificial Neural Network is all that is required in the contemporary situation. In this paper, CLBFFNN is presented as a special and intelligent form of artificial neural networks that has the capability to adapt to training and learning of new ideas and be able to give decisions in a trimodal biometric system involving fingerprints, face and iris biometric data. It gives an overview of neural networks.
This document provides an overview of applications of fuzzy logic in neural networks. It discusses fuzzy neurons as a combination of fuzzy logic and neural networks where the neuron's activation function is replaced with a fuzzy logic operation. Different types of fuzzy neurons are described, including OR, AND, and OR/AND fuzzy neurons. Supervised learning in fuzzy neural networks is also covered. The document concludes with advantages of fuzzy logic systems over traditional neural networks, such as the ability of fuzzy systems to systematically include linguistic knowledge.
Artificial Neural Networks (ANNS) For Prediction of California Bearing Ratio ...IJMER
The behaviour of soil at the location of the project and interactions of the earth materials during and after construction has a major influence on the success, economy and safety of the work. Another complexity associated with some geotechnical engineering materials, such as sand and gravel, is the difficulty in obtaining undisturbed samples and time consuming involving skilled
technician. Knowledge of California Bearing Ratio (C.B.R) is essential in finding the road thickness. To cope up with the difficulties involved, an attempt has been made to model C.B.R in terms of Fine Fraction, Liquid Limit, Plasticity Index, Maximum Dry density, and Optimum Moisture content. A multi-layer perceptron network with feed forward back propagation is used to model varying the
number of hidden layers. For this purposes 50 soils test data was collected from the laboratory test
results. Among the test data 30 soils data is used for training and remaining 20 soils for testing using
60-40 distribution. The architectures developed are 5-4-1, 5-5-1, and 5-6-1. Model with 5-6-1 architecture is found to be quite satisfactory in predicting C.B.R of soils. A graph is plotted between
the predicted values and observed values of outputs for training and testing process, from the graph it
is found that all the points are close to equality line, indicating predicted values are close to observed
values
Efficient design of feedforward network for pattern classificationIOSR Journals
This document compares the performance of radial basis function (RBF) networks and multi-layer perceptron (MLP) networks for pattern classification tasks. It analyzes the training time of RBF and MLP networks on two datasets: a below poverty line (BPL) dataset with 293 samples and 13 features, and a breast cancer dataset with 699 samples and 9 features. For both datasets, RBF networks trained significantly faster than MLP networks using the same number of hidden neurons, without affecting classification performance. The document concludes that RBF networks perform training faster than MLP networks for these pattern classification problems.
Similar to Capital market applications of neural networks etc (20)
Seminar: Gender Board Diversity through Ownership NetworksGRAPE
Seminar on gender diversity spillovers through ownership networks at FAME|GRAPE. Presenting novel research. Studies in economics and management using econometrics methods.
5 Tips for Creating Standard Financial ReportsEasyReports
Well-crafted financial reports serve as vital tools for decision-making and transparency within an organization. By following the undermentioned tips, you can create standardized financial reports that effectively communicate your company's financial health and performance to stakeholders.
"Does Foreign Direct Investment Negatively Affect Preservation of Culture in the Global South? Case Studies in Thailand and Cambodia."
Do elements of globalization, such as Foreign Direct Investment (FDI), negatively affect the ability of countries in the Global South to preserve their culture? This research aims to answer this question by employing a cross-sectional comparative case study analysis utilizing methods of difference. Thailand and Cambodia are compared as they are in the same region and have a similar culture. The metric of difference between Thailand and Cambodia is their ability to preserve their culture. This ability is operationalized by their respective attitudes towards FDI; Thailand imposes stringent regulations and limitations on FDI while Cambodia does not hesitate to accept most FDI and imposes fewer limitations. The evidence from this study suggests that FDI from globally influential countries with high gross domestic products (GDPs) (e.g. China, U.S.) challenges the ability of countries with lower GDPs (e.g. Cambodia) to protect their culture. Furthermore, the ability, or lack thereof, of the receiving countries to protect their culture is amplified by the existence and implementation of restrictive FDI policies imposed by their governments.
My study abroad in Bali, Indonesia, inspired this research topic as I noticed how globalization is changing the culture of its people. I learned their language and way of life which helped me understand the beauty and importance of cultural preservation. I believe we could all benefit from learning new perspectives as they could help us ideate solutions to contemporary issues and empathize with others.
In a tight labour market, job-seekers gain bargaining power and leverage it into greater job quality—at least, that’s the conventional wisdom.
Michael, LMIC Economist, presented findings that reveal a weakened relationship between labour market tightness and job quality indicators following the pandemic. Labour market tightness coincided with growth in real wages for only a portion of workers: those in low-wage jobs requiring little education. Several factors—including labour market composition, worker and employer behaviour, and labour market practices—have contributed to the absence of worker benefits. These will be investigated further in future work.
Abhay Bhutada, the Managing Director of Poonawalla Fincorp Limited, is an accomplished leader with over 15 years of experience in commercial and retail lending. A Qualified Chartered Accountant, he has been pivotal in leveraging technology to enhance financial services. Starting his career at Bank of India, he later founded TAB Capital Limited and co-founded Poonawalla Finance Private Limited, emphasizing digital lending. Under his leadership, Poonawalla Fincorp achieved a 'AAA' credit rating, integrating acquisitions and emphasizing corporate governance. Actively involved in industry forums and CSR initiatives, Abhay has been recognized with awards like "Young Entrepreneur of India 2017" and "40 under 40 Most Influential Leader for 2020-21." Personally, he values mindfulness, enjoys gardening, yoga, and sees every day as an opportunity for growth and improvement.
1. Elemental Economics - Introduction to mining.pdfNeal Brewster
After this first you should: Understand the nature of mining; have an awareness of the industry’s boundaries, corporate structure and size; appreciation the complex motivations and objectives of the industries’ various participants; know how mineral reserves are defined and estimated, and how they evolve over time.
STREETONOMICS: Exploring the Uncharted Territories of Informal Markets throug...sameer shah
Delve into the world of STREETONOMICS, where a team of 7 enthusiasts embarks on a journey to understand unorganized markets. By engaging with a coffee street vendor and crafting questionnaires, this project uncovers valuable insights into consumer behavior and market dynamics in informal settings."
The Rise of Generative AI in Finance: Reshaping the Industry with Synthetic DataChampak Jhagmag
In this presentation, we will explore the rise of generative AI in finance and its potential to reshape the industry. We will discuss how generative AI can be used to develop new products, combat fraud, and revolutionize risk management. Finally, we will address some of the ethical considerations and challenges associated with this powerful technology.
The Rise of Generative AI in Finance: Reshaping the Industry with Synthetic Data
Capital market applications of neural networks etc
1. Capital Market Applications of Neural Networks,
Fuzzy Logic and Genetic Algorithms
Arnold F. Shapiro
Penn State University
Smeal College of Business, University Park, PA 16802, USA
Phone: 01-814-865-3961, Fax: 01-814-865-6284, E-mail: afs1@psu.edu
Abstract: The capital markets have numerous areas with potential applications for neural net-
works, fuzzy logic and genetic algorithms. Given this potential and the impetus on these
technologies during the last decade, a number of studies have focused on capital market ap-
plications. This paper presents an overview of these studies. The specific purposes of the
paper are twofold: first, to review the capital market applications of these technologies so as
to document the unique characteristics of capital markets as an application area; and second,
to document the extent to which these technologies, and hybrids thereof, have been em-
ployed.
Keywords: capital markets, applications, neural networks, fuzzy logic, genetic algorithms
Acknowledgments:
This work was supported in part by the Robert G. Schwartz Faculty Fellowship. The assis-
tance of Asheesh Choudhary, Krishna D. Faldu, Jung Eun Kim, and Laura E. Campbell is
gratefully acknowledged
AFIR 2003_Shapiro_19.pdf 1
2. 1 Introduction
Neural networks (NNs) are used for learning and curve fitting, fuzzy logic (FL) is used to
deal with imprecision and uncertainty, and genetic algorithms (GAs) are used for search and
optimization. These technologies often are linked together because they are the most com-
monly used components of what Zadeh (1992) called soft computing (SC), which he envi-
sioned as being “... modes of computing in which precision is traded for tractability, robust-
ness and ease of implementation.”
The capital markets have numerous areas with potential applications for these SC technolo-
gies. Given this potential and the impetus on these technologies during the last decade, a
number of studies have focused on capital market applications and in many cases have dem-
onstrated better performance than competing approaches. This paper presents an overview of
these studies. The specific purposes of the paper are twofold: first, to review the capital mar-
ket applications of these SC technologies so as to document the unique characteristics of
capital markets as an application area; and second, to document the extent to which these
technologies, and hybrids thereof, have been employed.
The paper has a separate section devoted to each of the capital market areas of market fore-
casting, trading rules, option pricing, bond ratings, and portfolio construction. Each section
begins with a brief introduction and then SC studies in that application area are reviewed.
The studies were drawn from a broad cross-section of the literature and are intended to show
where each technology has made inroads into the capital market areas. However, since this
paper is still in the development stage, only a representative sample of the literature has been
included, so the study should be considered a work in progress. The paper ends with a prog-
nosis for the SC technologies.
2 Neural Networks, Fuzzy Logic and Genetic Algo-
rithms
It is assumed that readers are generally familiar with the basics of NNs, FL and GAs,1 but
they may not have conceptualized the overall processes associated with these technologies.
This section presents an overview of these processes.
2.1 Neural Networks (NNs)
NNs, first explored by Rosenblatt (1959) and Widrow and Hoff (1960), are computational
structures with learning and generalization capabilities. Conceptually, they employ a dis-
tributive technique to store knowledge acquired by learning with known samples and are
used for pattern classification, prediction and analysis, and control and optimization. Opera-
tionally, they are software programs that emulate the biological structure of the human brain
and its associated neural complex (Bishop, 1995).
The NN can be either supervised or unsupervised. The distinguishing feature of a supervised
NN is that its input and output are known and its objective is to discover a relationship be-
tween the two. The distinguishing feature of an unsupervised NN is that only the input is
AFIR 2003_Shapiro_19.pdf 2
3. known and the goal is to uncover patterns in the features of the input data. The remainder of
this subsection is devoted to an overview of supervised and unsupervised NNs, as processes.
2.1.1 Supervised NNs
A sketch of the operation of a supervised NN is shown in Figure 1.
Figure 1: The Operation of a Supervised NN
Since supervised learning is involved, the system will attempt to match the input with a
known target, such as stock prices or bond ratings. The process begins by assigning random
weights to the connection between each set of neurons in the network. These weights repre-
sent the intensity of the connection between any two neurons. Given the weights, the inter-
mediate values (in the hidden layer) and then the output of the system are computed. If the
output is optimal, in the sense that it is sufficiently close to the target, the process is halted; if
not, the weights are adjusted and the process is continued until an optimal solution is ob-
tained or an alternate stopping rule is reached.
If the flow of information through the network is from the input to the output, it is known as a
feed forward network. The NN is said to involve back-propagation if inadequacies in the
output are fed back through the network so that the algorithm can be improved. We will refer
to this network as a feedforward NN with backpropagation (FFNN with BP).
2.1.2 Unsupervised NNs
This section discusses one of the most common unsupervised NNs, the Kohonen network
(Kohonen 1988), which often is referred to as a self-organizing feature map (SOFM). The
purpose of the network is to emulate our understanding of how the brain uses spatial map-
pings to model complex data structures. Specifically, the learning algorithm develops a map-
ping from the input patterns to the output units that embodies the features of the input pat-
terns.
In contrast to the supervised network, where the neurons are arranged in layers, in the Koho-
nen network they are arranged in a planar configuration and the inputs are connected to each
unit in the network. The configuration is depicted in Figure 2.
AFIR 2003_Shapiro_19.pdf 3
4. Figure 2: Two Dimensional Kohonen Network
As indicated, the Kohonen SOFM may be represented as a two-layered network consisting of
a set of input units in the input layer and a set of output units arranged in a grid called a Ko-
honen layer. The input and output layers are totally interconnected and there is a weight as-
sociated with each link, which is a measure of the intensity of the link.
The sketch of the operation of a SOFM is shown in Figure 3.
Figure 3: Operation of a Kohonen Network
The first step in the process is to initialize the parameters and organize the data. This entails
setting the iteration index, t, to zero, the interconnecting weights to small positive random
values, and the learning rate to a value smaller than but close to 1. Each unit has a neighbor-
hood of units associated with it and empirical evidence suggests that the best approach is to
have the neighborhoods fairly broad initially and then to have them decrease over time.
Similarly, the learning rate is a decreasing function of time.
Each iteration begins by randomizing the training sample, which is composed of P patterns,
each of which is represented by a numerical vector. For example, the patterns may be com-
posed of stocks and/or market indexes and the input variables may be daily price and volume
data. Until the number of patterns used (p) exceeds the number available (p > P), the patterns
are presented to the units on the grid, each of which is assigned the Euclidean distance be-
tween its connecting weight to the input unit and the value of the input. This distance is
given by [Σj ( xj - wij )2]0.5, where wij is the connecting weight between the j-th input unit and
the i-th unit on the grid and xj is the input from unit j. The unit that is the best match to the
pattern, the winning unit, is used to adjust the weights of the units in its neighborhood. For
AFIR 2003_Shapiro_19.pdf 4
5. this reason the SOFM is often referred to as a competitive NN. The process continues until
the number of iterations exceeds some predetermined value (T).
In the foregoing training process, the winning units in the Kohonen layer develop clusters of
neighbors, which represent the class types found in the training patterns. As a result, patterns
associated with each other in the input space will be mapped to output units that also are as-
sociated with each other. Since the class of each cluster is known, the network can be used to
classify the inputs.
2.2 Fuzzy Logic (FL)
Fuzzy logic2 (FL), which was formulated by Zadeh (1965), was developed as a response to
the fact that most of the parameters we encounter in the real world are not precisely defined.
As such, it gives a framework for approximate reasoning and allows qualitative knowledge
about a problem to be translated into an executable set of rules. This reasoning and rule-
based approach, which is known as a fuzzy inference system, is then used to respond to new
inputs.
2.2.1 A Fuzzy Inference System (FIS)
The fuzzy inference system (FIS) is a popular methodology for implementing FL.3 FISs are
also known as fuzzy rule based systems, fuzzy expert systems, fuzzy models, fuzzy associa-
tive memories (FAM), or fuzzy logic controllers when used as controllers (Jang et al. 1997
p. 73). The essence of the system can be represented as shown in Figure 4.
Figure 4: A Fuzzy Inference System (FIS)
As indicated in the figure, the FIS can be envisioned as involving a knowledge base and a
processing stage. The knowledge base provides the membership functions (MFs) and fuzzy
rules needed for the process. In the processing stage, numerical crisp variables are the input
of the system.4 These variables are passed through a fuzzification stage where they are trans-
formed to linguistic variables, which become the fuzzy input for the inference engine. This
fuzzy input is transformed by the rules of the inference engine to fuzzy output. The linguistic
results are then changed by a defuzzification stage into numerical values that become the
output of the system.
AFIR 2003_Shapiro_19.pdf 5
6. 2.3 Genetic Algorithms (GAs)
Genetic algorithms5 (GAs) were proposed by Holland (1975) as a way to perform a random-
ized global search in a solution space. In this space, a population of candidate solutions, each
with an associated fitness value, is evaluated by a fitness function on the basis of their per-
formance. Then, using genetic operations, the best candidates are used to evolve a new popu-
lation that not only has more of the good solutions but better solutions as well.
This process, which can be described as an automated, intelligent approach to trial and error,
based on principles of natural selection, is depicted in Figure 5.
Figure 5: The GA Process
As indicated, the first step in the process is initialization, which involves choosing a popula-
tion size (M), population regeneration factors, and a termination criterion. The next step is to
randomly generate an initial population of solutions, P(g=0), where g is the generation. If
this population satisfies the termination criterion, the process stops. Otherwise, the fitness of
each individual in the population is evaluated and the best solutions are "bred" with each
other to form a new population, P(g+1); the poorer solutions are discarded. If the new popu-
lation does not satisfy the termination criterion, the process continues.
2.3.1 Population Regeneration Factors
There are three common ways to develop a new generation of solutions: reproduction, cross-
over, and mutation. Reproduction adds a copy of a fit individual to the next generation.
Crossover emulates the process of creating children, and involves the creation of new indi-
viduals (children) from the two fit parents by a recombination of their genes (parameters).
Under mutation, there is a small probability that some of the gene values in the population
will be replaced with randomly generated values. This has the potential effect of introducing
good gene values that may not have occurred in the initial population or which were elimi-
nated during the iterations. In Figure 5, the process is repeated until the new generation has
the same number of individuals (M) as the previous one.
AFIR 2003_Shapiro_19.pdf 6
7. 3 Market Forecasting
Market forecasting involves projecting such things stock market indexes, like the Standard
and Poor's (S&P) 500 stock index, Treasury bill rates, and net asset value of mutual funds.
The role of SC in this case is to use quantitative inputs, like technical indices, and qualitative
factors, like political effects, to automate stock market forecasting and trend analysis. This
section provides an overview of representative SC studies in this area.
Apparently, White (1988) was the first to use NNs for market forecasting. He was curious as
to whether NNs could be used to extract nonlinear regularities from economic time series,
and thereby decode previously undetected regularities in asset price movements, such as fluc-
tuations of common stock prices. The purpose of his paper was to illustrate how the search
for such regularities using a feed-forward NN (FFNN) might proceed, using the case of IBM
daily common stock returns as an example. White found that his training results were over-
optimistic, being the result of over-fitting or of learning evanescent features. He concluded,
"the present neural network is not a money machine."
Chiang et. al. (1996) used a FFNN with backpropagation (BP) to forecast the end-of-year net
asset value (NAV) of mutual funds, where the latter was predicted using historical economic
information. They compared those results with results obtained using traditional econometric
techniques and concluded that NNs "significantly outperform regression models " when lim-
ited data is available.
Kuo et. al. (1996), recognized that qualitative factors, like political effects, always play a
very important role in the stock market environment, and proposed an intelligent stock mar-
ket forecasting system that incorporates both quantitative and qualitative factors. This was
accomplished by integrating a NN and a fuzzy Delphi model (Bojadziev and Bojadziev, 1997
p. 71); the former was used for quantitative analysis and decision integration, while the later
formed the basis of the qualitative model. They applied their system to the Taiwan stock
market.
Kim and Chun (1998) used a refined probabilistic NN (PNN), called an arrayed probabilistic
network (APN), to predict a stock market index. The essential feature of the APN was that it
produces a graded forecast of multiple discrete values rather than a single bipolar output. As
a part of their study, they use a "mistake chart," which benchmarks against a constant predic-
tion, to compare FFNN with BP models with a PNN, APN, recurrent NN (RNN), and case
based reasoning. They concluded that the APN tended to outperform recurrent and BP net-
works, but that case base reasoning tended to outperform all the networks.
Aiken and Bsat (1999) use a FFNN trained by a genetic algorithm (GA) to forecast three-
month U.S. Treasury Bill rates. They conclude that an NN can be used to accurately predict
these rates.
Edelman et. al. (1999) investigated the use of an identically structured and independently
trained committee of NNs to identify arbitrage opportunities in the Australian All-Ordinaries
Index. Trading decisions were made based on the unanimous consensus of the committee
predictions and the Sharpe Index was used to assess out-of-sample trading performance.
Empirical results showed that technical trading based on NN predictions outperformed the
AFIR 2003_Shapiro_19.pdf 7
8. buy-and-hold strategy as well as "naive prediction". They concluded that the reliability of
the network predictions and hence trading performance was dramatically enhanced by the use
of trading thresholds and the committee approach.
Thammano (1999) used a neuro-fuzzy model to predict future values of Thailand's largest
government-owned bank The inputs of the model were the closing prices for the current and
prior three months, and the profitability ratios ROA, ROE and P/E. The output of the model
was the stock prices for the following three months. He concluded that the neuro-fuzzy ar-
chitecture was able to recognize the general characteristics of the stock market faster and
more accurately than the basic backpropagation algorithm. Also, it could predict investment
opportunities during the economic crisis when statistical approaches did not yield satisfactory
results.
Trafalis (1999) used FFNNs with BP and the weekly changes in 14 indicators to forecast the
change in the S&P 500 stock index during the subsequent week. In addition, a methodology
for pre-processing of the data was devised, which involved differencing and normalizing the
data, was successfully implemented. The text walked the reader though the NN process.
Tansel et. al. (1999) compared the ability of linear optimization, NNs, and GAs to model time
series data using the criteria of modeling accuracy, convenience and computational time.
They found that linear optimization methods gave the best estimates, although the GAs could
provide the same values if the boundaries of the parameters and the resolution were selected
appropriately, but that the NNs resulted in the worst estimations. However, they noted that
non-linearity could be accommodated by both the GAs and the NNs and that the latter re-
quired minimal theoretical background.
Garliauskas (1999) investigated stock market time series forecasting using a NN computa-
tional algorithm linked with the kernel function approach and the recursive prediction error
method. The main idea of NN learning by the kernel function is that the function stimulates
to changes of the weights in order to achieve convergence of the target and forecast output
functions. He concluded that financial times series forecasts by the NNs were superior to
classical statistical and other methods.
Chan et. al. (2000) investigated financial time series forecasting using a FFNN and daily
trade data from the Shanghai Stock Exchange. To improve speed and convergence they used
a conjugate gradient learning algorithm and used multiple linear regression (MLR) for the
weight initialization. They conclude that the NN can model the time series satisfactorily and
that their learning and initialization approaches lead to improved learning and lower compu-
tation costs.
Kim and Han (2000) used a NN modified by a GA to predict the stock price index. In this
instance, the GA was used to reduce the complexity of the feature space, by optimizing the
thresholds for feature discretization, and to optimize the connection weights between layers.
Their goal was to use globally searched feature discretization to reduce the dimensionality of
the feature space, eliminates irrelevant factors, and to mitigate the limitations of gradient de-
scent. They concluded that the GA approach outperformed the conventional models.
Romahi and Shen (2000) developed an evolving rule based expert system for financial fore-
casting. Their approach was to merge FL and rule induction so as to develop a system with
AFIR 2003_Shapiro_19.pdf 8
9. generalization capability and high comprehensibility. In this way the changing market dy-
namics are continuously taken into account as time progresses and the rulebase does not be-
come outdated. They concluded that the methodology showed promise.
Abraham et. al. (2001) investigated hybridized SC techniques for automated stock market
forecasting and trend analysis. They used principal component analysis to preprocess the in-
put data, a NN for one-day-ahead stock forecasting and a neuro-fuzzy system for analyzing
the trend of the predicted stock values. To demonstrate the proposed technique, they ana-
lyzed 24 months of stock data for the Nasdaq-100 main index as well as six of the companies
listed therein. They concluded that the forecasting and trend prediction results using the pro-
posed hybrid system were promising and warranted further research and analysis.
Cao and Tay (2001) used Support Vector Machines (SVMs) to study the S&P 500 daily price
index. The generalization error with respect to the free parameters of SVMs were investi-
gated and found to have little impact on the solution. They conclude that it is advantageous
to apply SVMs to forecast the financial time series.
Hwarng (2001) investigated NN forecasting of time series with ARMA (p,q) structures. Us-
ing simulation and the performance of the Box-Jenkins model as a benchmark, it was con-
cluded that FFNN with BP generally performed well and consistently for time series corre-
sponding to ARMA(p,q) structures. Using the randomized complete block design of experi-
ment, he concluded that overall, for most of the structures, FFNN with BP performed signifi-
cantly better when a particular noise level was considered during network training
As a follow-up to Kuo et. al. (1996), Kuo et. al. (2001) developed a GA-based FNN (GFNN)
to formulate the knowledge base of fuzzy inference rules, which can measure the qualitative
effect (such as the political effect) in the stock market. The effect was further integrated with
the technical indexes through the NN. Using the clarity of buying-selling points and buying-
selling performance based on the Taiwan stock market to assess the proposed intelligent sys-
tem, they conclude that a NN based on both quantitative (technical indexes) and qualitative
factors is superior to one based only on quantitative factors.
4 Trading Rules
If one dollar were invested in 1926 in 1-month U.S. Treasury bills, it would have grown to
$14 by December 1996. If that dollar had been invested in the S&P 500, it would have
grown to $1,370 during that period. If the dollar had been invested with monthly switching
to either Treasury bills or the S&P 500, whichever asset would perform the best during that
month, it would have grown to over $2 billion dollars during that period.6 Timing clearly is
relevant and it is not surprising that trading rules have evolved that purport to optimize
buy/sell timing decisions.
Of course, the extent to which timing is feasible is controversial. Sharp (1975) was skeptical
that market timing could be profitable and Droms (1989) concluded that successful timing
requires forecasting accuracy beyond the ability of most managers. Nonetheless, researchers
continue to explore and enhance trading rules, driven, in large part, by the expanding tech-
nology. The goal of SC, as it pertains to trading rules, is to create a security trading decision
support system, which, ideally, is fully automated and triggered by both quantitative and
AFIR 2003_Shapiro_19.pdf 9
10. qualitative factors. This section provides an overview of representative SC studies in this
area.
Kosaka et. al. (1991) demonstrated the effectiveness of applying FL and NNs to buy/sell tim-
ing detection and stock portfolio selection. They reported that in a test of their model's abil-
ity to follow price trends, it correctly identified 65% of all price turning points.
Wilson (1994) developed a fully automatic stock trading system that took in daily price and
volume data on a list of 200 stocks and 10 market indexes and produced a set of risk-reward
ranked alternate portfolios. The author implemented a five step procedure: a chaos-based
modeling procedure was used to construct alternate price prediction models based on techni-
cal, adaptive, and statistical models; then, a SOFM was used to select the best model for each
stock or index on a daily basis; then, a second SOFM was used to make a short-term gain-
loss prediction for each model; then, a trade selection module combined these predictions to
generate buy-sell-hold recommendations for the entire list of stocks on a daily basis; and fi-
nally, a portfolio management utility combined the trading recommendations to produce the
risk-reward ranked portfolios. He concluded that the stock trading systems could produce
better results than index funds and at the same time reduce risk.
Frick et. al. (1996) investigated price-based heuristic trading rules for buying and selling
shares. Their methodology involved transforming the time series of share prices using a heu-
ristic charting method that gave buy and sell signals and was based on price change and re-
versals. Based on a binary representation of those charts, they used GAs to generate trade
strategies from the classification of different price formations. They used two different
evaluation methods: one compared the return of a trading strategy with the corresponding
riskless interest rate and the average stock market return; the other used its risk-adjusted ex-
pected return as a benchmark instead of the average stock market return. Their analysis of
over one million intra-day stock prices from the Frankfurt Stock Exchange (FSE) showed the
extent to which different price formations could be classified by their system and the nature
of the rules, but left for future research an analysis of the performance of the resulting trading
strategies.
Kassicieh et. al. (1997) examined the performance of GAs when used as a method for formu-
lating market-timing trading rules. Their goal was to develop a monthly strategy for deciding
whether to be fully invested in a broad based stock portfolio, the S&P 500, or a riskless in-
vestment, treasury bills. Following the methodology of Bauer (1994), their inputs were dif-
ferenced time series of 10 economic indicators and the GA used the best three of these series
to make the timing (switching) decision. They benchmarked against the dollar accumulation
given a perfect timing strategy, and concluded that their runs produced excellent results.
As a follow-up study, Kassicieh et. al. (1998) used the same GA with different data transfor-
mation methods applied to economic data series. These methods were the singular value de-
composition (SVD) and principal component NN with 3, 4, 5 and 10 nodes in the hidden
layer. They found that the non standardized SVD of economic data yielded the highest ter-
minal wealth for the time period examined.
Allen and Karjalainen (1999) used a GA to learn technical trading rules for the S&P 500 in-
dex using daily prices from 1928 to 1995. However, after transaction costs, the rules did not
earn consistent excess returns over a simple buy-and-hold strategy in the out-of-sample test
AFIR 2003_Shapiro_19.pdf 10
11. periods. The rules were able to identify periods to be in the index when daily returns were
positive and volatility was low and out of the index when the reverse was true, but these latter
results could largely be explained by low-order serial correlation in stock index returns.
Fernandez-Rodriguez et. al. (1999) investigated the profitability of a simple technical trading
rule based on NNs applied to the General Index of the Madrid Stock Market. They found
that, in the absence of trading costs, the technical trading rule is always superior to a buy-
and-hold strategy for both "bear" and "stable" markets but that the reverse holds during a
"bull" market.
Baba et. al. (2000) used NNs and GAs to construct an intelligent decision support system
(DSS) for analyzing the Tokyo Stock Exchange Prices Indexes (TOPIX). The essential fea-
ture of their DSS was that it projected the high and low TOPIX values four weeks into the
future and suggested buy and sell decisions based on the average projected value and the
then-current value of the TOPIX. To this end, they construct an (8, 15, 2) FFNN using a hy-
brid weight-training algorithm that combines a modified BP method with a random optimiza-
tion method. Initially, the buy-sell decision was on an all-or-nothing basis; subsequently, us-
ing the GAs, an algorithm was developed for buying or selling just a portion of the shares.
They conclude that NNs and GAs could be powerful tools for dealing with the TOPIX.
5 Option Pricing
This section provides an overview of the use of SC technologies for pricing options. As ex-
pected, the Black-Scholes option pricing model was a benchmark for many of the SC solu-
tions. On the one hand, the issue was the extent to which the SC out-of-sample performance
could duplicate the Black-Scholes result; on the other hand, the issue was the extent to which
the SC model could outperform the Black-Scholes model. Another line of inquiry was re-
lated to methods for estimating the volatility7 of options, and involved a comparison of im-
plied volatility, historical volatility, and a SC-derived volatility. Other topics addressed in-
cluded common option features used for SC modeling and specific types of options that have
been modeled. This section gives an overview of these SC applications.
Malliaris and Salchenberger (1994) compared the estimated volatility of daily S&P 100 Index
stock market options using implied volatility, historical volatility, and a volatility based on a
FFNN (13-9-1) with BP. They used the following 13 features: change in closing price, days
to expiration, change in open put volume, the sum of the at-the-money strike price and mar-
ket price of the option for both calls and puts for the current trading period and the next trad-
ing period, daily closing volatility for current period, daily closing volatility for next trading
period, and four lagged volatility variables. They concluded that the NN was far superior to
the historical method.
Chen and Lee (1997) illustrated how GAs, as an alternative to NNs, could be used for option
pricing. To this end, they tested the ability of GAs to determine the price of European call
options, assuming the exact price could be determined using Black-Scholes option pricing
theory. They conclude that the results were encouraging.
Anders et. al. (1998) used statistical inference techniques to build NN models to explain the
prices of call options written on the German stock index DAX. Some insight into the pricing
AFIR 2003_Shapiro_19.pdf 11
12. process of the option market was obtained by testing for the explanatory power of several NN
inputs. Their results indicated that statistical specification strategies lead to parsimonious
NNs with superior out-of-sample performance when compared to the Black-Scholes model.
They further validated their results by providing plausible hedge parameters.
Gottschling et. al. (1999) discussed a novel way to price a European call option using a pro-
posed new family of density functions and the flexible structure of NNs. The density func-
tions were based upon the logarithm of the inverse Box-Cox transform8. Essentially, they
viewed the activation function of a NN as a univariate pdf and constructed their family of
probability density functions, which have the property of closed form integrability, as the
output of a single hidden layer NN. Then, observing that the price of a European call option
could be expressed in terms of an integral of the cumulative distribution function of risk neu-
tralized asset returns, they derived a closed form expression from which the free parameters
could then be estimated.
Yao et. al. (2000) use a FFNN with BP to forecast the option prices of the Nikkei 225 index
futures. Different data groupings affected the accuracy of the results and they concluded that
the data should be partitioned according to moneyness (the quotient of stock prices to strike
prices). Their results suggested that for volatile markets a NN option-pricing model outper-
forms the traditional Black-Scholes model, while the Black-Scholes model is appropriate for
pricing at-the-money options.
Amilon (2001) examined whether a FFNN with BP could be used to find a call option pricing
formula that corresponded better to market prices and the properties of the underlying asset
than the Black-Scholes formula. The goal was to model a mapping of some input variable
onto the observed option prices and to benchmark against the Black-Scholes model using his-
torical and implicit volatility estimates. He found that, although the NNs were superior in the
sense that they outperform the benchmarks both in pricing and hedging performances, the
results often were insignificant at the 5% level.
6 Bond Ratings
Bond ratings are subjective opinions on the ability to service interest and debt by economic
entities such as industrial and financial companies, municipals, and public utilities. They are
published by major bond rating agencies, like Moody's and Standard & Poor's, who guard
their exact determinants. Several attempts have been made to model these bond ratings, us-
ing methods such as linear regression and multiple discriminant analysis, and in recent years
SC has been applied to the problem. This section provides an overview of three such SC
studies.
Surkan and Ying (1991) investigated the feasibility of bond rating formulas derived through
simplifying a trained FFNN with BP. Under their method, features are systematically elimi-
nated, based on the magnitude of the weights of the hidden layer and subject to error toler-
ance constraints, until all that remains is a simple, minimal network. The network weights
then provide information for the construction of a mathematical formula. In their example,
the result of refining the network model was a reduction from the seven features provided in
the original financial data to only the two that contribute most to bond rating estimates. The
derived formula was found to generalize very well.
AFIR 2003_Shapiro_19.pdf 12
13. Although not specifically addressing bond ratings, one example of how FL could be applied
to bonds was provided by Hosler (1992 p. 15), who showed how MFs could be used to de-
scribe the risk of call of a security. She noted that randomness is associated with the behav-
ior of market interest rates and that fuzziness arises from the subjective opinion of the inves-
tor. The function could be altered to reflect the desirability of the security based upon the call
risk.
Daniels and Kamp (1999) applied NNs to bond rating, with a special emphasis on the flexi-
bility of the NNs and their validity, especially when the number of observations is small.
Their aim was to establish a general network construction procedure and, to that end, they
discussed how techniques such as cross-validation and monotonicity analysis9 can be effec-
tively combined to optimize the NN. A special class of monotonic NNs and a corresponding
training algorithm were developed.
7 Portfolio Construction
Portfolio construction is that part of the investment process that involves the determination of
which assets to invest in and the proportion of funds to invest in each of the assets. At a
minimum, effective portfolio optimization involves simultaneously maximizing the portfolio
return and minimizing the portfolio risk, subject to various constraints, but it also can involve
such things as maximizing the possibility of reaching higher returns. This section provides
an overview of some of the SC studies in this area.
Lowe (1994) demonstrated the use of NNs in two types of capital market problems: effective
portfolio optimization and short-term prediction of multiple equities. Assuming the existence
of a market portfolio, his first goal was to find an approximating portfolio that minimized the
"risk," defined in terms of the mean squared error between the market portfolio and the ap-
proximating portfolio, subject to constraints, which he transformed into an analytic cost func-
tion, and resolved using an analog NN. He viewed short-term equities prediction as a prob-
lem in nonlinear multichannel time series forecasting, which can be addressed by a FFNN
and resolved using a radial basis function. The network then was used to predict the one
stock in the approximating portfolio that would gain the most in the next investment period.
Wendt (1995) used a GA to build a portfolio efficient frontier. The underlying data consisted
of 250 scenarios of annual returns for eight asset classes. To evaluate the GA process, the
final GA output was compared to the efficient frontier created by a sophisticated nonlinear
optimizer. After about 50 cycles, the GA found portfolios very close to the efficient frontier
generated by the nonlinear optimizer.
Guo and Huang (1996) used a possibilistic linear programming method for optimal asset al-
location based on simultaneously maximizing the portfolio return, minimizing the portfolio
risk and maximizing the possibility of reaching higher returns. This was analogous to maxi-
mizing mean return, minimizing variance and maximizing skewness for a random rate of re-
turn.
AFIR 2003_Shapiro_19.pdf 13
14. The authors conceptualized the possibility distribution of the imprecise rate of return of the i-
th asset of the portfolio as the fuzzy number ~i = (rip , rim , rio ) , where rip , rim , rio were the most
r
pessimistic value, the most possible value, and the most optimistic value for the rate of re-
turn, respectively. Then, taking the weighted averages of these values, they defined the im-
precise rate of return for the entire portfolio as ~ = (r p , r m , r o ) , the portfolio risk as (r m - r p ),
r
and the portfolio skewness as (r o - r m ). The authors then showed in a step-by-step fashion
how the portfolio could be optimized using Zimmermann's (1978) fuzzy programming
method. The authors conclude that their algorithm provided maximal flexibility for decision
makers to effectively balance the portfolio's return and risk.
Jackson (1997) applied a GA to the problem of asset allocation, first using the traditional
mean variance approach and then using a direct utility maximization method for a step utility
function. As a benchmark, he compared the performance of GAs with Newton's method of
optimization. In the first case, he assumed the fund was maximizing the expected utility of
wealth, which lead to a quadratic objective function. He found that the portfolio composi-
tions were similar for both the Newton method and the GA, but that the GA took considera-
bly longer to optimize the portfolio. In the second case, where the fund had a step utility
function, Newton's method was very unstable, as a gradient-based method has difficulty with
steps in the utility function, and produced different results for different starting values. In
contrast, the GA was more robust to discontinuities in the search space, and not as sensitive
to the starting values.
8 Comment
The purpose of this article has been to provide the reader with an overview of where NNs, FL
and GAs have been implemented in the capital markets and to document the manner in which
these SC technologies were employed. Based on these studies, there is ample evidence that
SC have made inroads into many facets of the capital markets. As we improve our under-
standing of the strengths and weaknesses of the SC technologies and improve the manner by
which we leverage their best features, it seems inevitable that SC will become one of our im-
portant tools for analyzing capital markets.
References
Abraham, A., B. Nath and P. K. Mahanti. (2001) "Hybrid Intelligent Systems for Stock Mar-
ket Analysis," Computational Science, Springer-Verlag Germany, Vassil N. Alexan-
drov et. al. (Eds.), ISBN 3-540-42233-1, San Francisco, USA, pp. 337-345.
Aiken, M. and M. Bsat. (1999) “Forecasting Market Trends with Neural Networks.” Infor-
mation Systems Management 16 (4), 42-48.
Alemdar, N. M. and S. Özyildirim. (1998) A genetic game of trade, growth and external-
ities.” Journal of Economic Dynamics and Control 22, 811-832.
AFIR 2003_Shapiro_19.pdf 14
15. Allen, F. and R. Karjalainen. (1999) "Using genetic algorithms to find technical trading
rules," Journal of Financial Economics 51: 245–271
Amilon, H. (2001) “A Neural Network Versus Black-Scholes: A Comparison of Pricing and
Hedging Performances.” Department of Economics, Lund University, Lund, Sweden.
Anders, U., O. Korn and C. Schmitt. (1998) “Improving the Pricing of Options:
A Neural Network Approach.” Journal of Forecasting 17 (5-6), 369-388.
Baba, N., N. Inoue and H. Asakawa. (2000) "Utilization of Neural Networks & GAs for
Constructing Reliable Decision Support Systems to Deal Stocks." Working paper of
Information Science, Osaka-Kyoiku University, Asahiga-Oka, 4-698-1, Kashiwara
City, Osaka Prefecture, 582-8582, Japan.
Bezdek, J.C. (1981) Pattern Recognition with Fuzzy Objective Function Algorithms, Plenum
Press, New York.
Bishop, C. M. (1995) Neural Networks for Pattern Recognition, Clarendon Press.
Bojadziev, G. and Bojadziev, M. (1997) Fuzzy Logic for Business, Finance and Manage-
ment. World Scientific, Singapore.
Brockett, P. L., Xia, X., and Derrig, R. A. (1998) “Using Kohonen's Self-Organizing Feature
Map to Uncover Automobile Bodily Injury Claims Fraud,” J Risk and Insurance
65(2), pp. 245-274.
Cao, L. and F. E. H. Tay. (2001) "Financial Forecasting Using Support Vector Machines,"
Neural Comput & Applic (2001) 10: 184–192.
Chan, M-C, C-C Wong, and C-C Lam. (2000) “Financial Time Series Forecasting by Neural
Network Using Conjugate Gradient Learning Algorithm and Multiple Linear Regres-
sion Weight Initialization,” Department of Computing, The Hong Kong Polytechnic
University, Kowloon, Hong Kong.
Chen, S.-H. and W.-C. Lee. (1997) “Option Pricing with Genetic Algorithms: A Second Re-
port.” IEEE. 21-25.
Chiang, W.-C., T. L. Urban and G. W. Baldridge. (1996) “A Neural Network Approach to
Mutual Fund Net Asset Value Forecasting.” Omega, Int. J. Mgmt Sci. 24 (2), 205-
215.
Daniels, H and B. Kamp. (1999) “Applications of MLP networks to bond rating and house
pricing.” Neural Computing and Applications 8 (3), 226-234.
Datz, J. O. and D. L. McCormick. (2000). The Encyclopedia of Trading Strategies, New
York: McGraw-Hill.
Droms, W. G. (1989) "Market Timing as an Investment Policy," Financial Analysts Journal,
January/February, pp. 73-77.
AFIR 2003_Shapiro_19.pdf 15
16. Edelman, D., P. Davy and Y. L. Chung. (1999) “Using Neural Network Prediction to achieve
excess returns in the Australian All-Ordinaries Index”. In: Queensland Financial
Conference, Sept 30th & Oct 1st, Queensland University of Technology
Falas, T., A. Charitou and C. Charalambous. (1994) “The Application of Artificial Neural
Networks in the Prediction of Earnings.” IEEE International Conference on Neural
Networks 6, 3629-3633. 27 June-2 July.
Farmer, J. D. and A. W. Lo. (1999) "Frontiers of finance: Evolution and efficient markets,"
Proc. Natl. Acad. Sci. USA Vol. 96, pp. 9991–9992.
Fernandez-Rodriguez, F., C. González-Martel and S. Sosvilla-Rivero. (1999) “On the Profit-
ability of Technical Trading Rules Based on Artificial Neural Networks: evidence
from the Madrid Stock Market.” Working Paper.
Francis, L. (2001), “Neural Networks Demystified,” Casualty Actuarial Society Forum, Win-
ter, pp. 253-319.
Frick, A., R. Herrmann, M. Kreidler, A. Narr and D. Seese. (1996) “Genetic-Based Trading
Rules-A New Tool to Beat the Market With? – First Empirical Results.” AFIR Vol. 2,
997-1017.
Garliauskas, A. (1999) “Neural Network Chaos and Computational Algorithms of Forecast
in Finance.” Proceedings of the IEEE SMC Conference on Systems, Man, and Cy-
bernetics 2, 638-643. 12-15 October.
Gottschling, A., C. Haefke, and H. White. (1999) “Closed Form Integration of Artificial Neu-
ral Networks with Some Applications to Finance.” Working Paper
Guo, L. and Z. Huang. (1996) “A Possibilistic Linear Programming Method for Asset Alloca-
tion,” Journal of Actuarial Practice, 2(1):67-90.
Holland, J.H. (1975) Adaptation in Natural and Artificial Systems, MIT Press, Cambridge,
MA.
Hosler, V. R. 1992. "The Application of Fuzzy Sets to Group Health Underwriting," ARCH
2, pp. 1-63.
Hwarng, H. B. (2001) “Insights into Neural-Network Forecasting of Time Series Corre-
sponding to ARMA (p,q) Structures.” International Journal of Management Science,
Omega, 29, 273-289.
Jackson, A. (1997) “Genetic Algorithms for Use in Financial Problems.” AFIR Vol 2, 481-
503.
Jang, J-S.R., Sun, C-T., and Mizutani, E. (1997) Neuro-fuzzy and soft computing: a compu-
tational approach to learning and machine intelligence, Prentice Hall, Upper Saddle
River, NJ.
AFIR 2003_Shapiro_19.pdf 16
17. Kassicieh, S. K., T. L. Paez and G. Vora. (1997) “Investment Decisions Using Genetic Al-
gorithms.” Proceedings of the Thirtieth Hawaii International Conference on System
Sciences 5, 484-490. 7-10 January.
Kassicieh, S. K., T. L. Paez and G. Vora. (1998) “Data Transformation Methods for Genetic-
Algorithm-Based Investment Decisions.” Proceedings of the Thirty-First Hawaii In-
ternational Conference on System Sciences 5, 122-127. 6-9 January.
Kim, S. H. and S. H. Chun. (1998) “Graded forecasting using an array of bipolar predictions:
application of probabilistic neural networks to a stock market index.” International
Journal of Forecasting. 14, 323-337.
Kim, K-J. and I. Han. (2000) “Genetic algorithms approach to feature discretization in artifi-
cial neural networks for the prediction of stock price index.” Published by Elsevier
Science, Ltd., Expert Systems with Applications, 19, 125-132.
Kohonen, T. (1988) "Self-Organizing Feature Maps,” Self-Organizing and Associative
Memory, 2nd ed. Spring-Verlag, Berlin, Heidelberg, Germany.
Kosaka, M., H. Mizuno, T. Sasaki, R. Someya and N. Hamada. (1991) “Applications of
fuzzy logic/neural network to securities trading decision support system.” Proceed-
ings of the IEEE conference on Systems, Man, and Cybernetics 3: 1913-1918. 13-16
October.
Kuo, R. J., C. H. Chen and Y. C. Hwang. (2001) "An intelligent stock trading decision sup-
port system through integration of genetic algorithm based fuzzy neural network and
artificial neural network," Fuzzy Sets and Systems: 118 (1) (2001) pp. 21-45.
Kuo, R. J., L. C. Lee and C. F. Lee. (1996) “Integration of Artificial Neutal Networks and
Fuzzy Delphi for Stock Market Forecasting.” IEEE, June, 1073-1078.
Lowe, D. (1994) “Novel Exploitation of Neural Network Methods in Financial Markets.”
IEEE International Conference on Neural Networks 6, 3623-3628. 27 June-2 July.
Malliaris, M. and L. Salchenberger. (1994) “Do-ahead replaces run-time: a neural network
forecasts options volatility.” Proceedings of the Tenth Conference on Artificial Intel-
ligence for Applications, 480-481. 1-4 March.
Neely, C. J. and P. A.Weller. (2002) " Predicting Exchange Rate Volatility: Genetic Pro-
gramming Versus GARCH and RiskMetrics," The Federal Reserve Bank of St. Louis
84(3): 43-54.
Rast, M. (1997) “Forecasting Financial Time Series with Fuzzy Neural Networks.” IEEE
International Conference Intelligent Processing Systems 1, 432–434. 28-31 October.
Refenes, A_P. 1995. Neural Networks in the Capital Markets. New York: John Wiley &
Sons.
AFIR 2003_Shapiro_19.pdf 17
18. Refenes, A.-P. N., Y. Abu-Mostafa, J. Moody and A. Weigend. (1995) Neural Networks in
Financial Engineering, London: World Scientific Publisjhing Company.
Resta, M. (2000a) “ATA: The Artificial Technical Analyst Building Intra-Day Market Strate-
gies.” IEEE, 729-732.
Resta, M. (2000c) “Towards an Artificial Technical Analysis?” IEEE Transactions on Neural
Networks, Vol. XX, No. Y, 100-105.
Resta, M. (2000d) “Towards an Artificial Technical Analysis of Financial Markets.” IEEE
Transactions on Neural Networks, Vol. XX, No. Y, 117-122.
Romahi, Y. and Q. Shen. (2000) “Dynamic Financial Forecasting with Automatically In-
duced Fuzzy Associations.” IEEE, 493-498.
Rosenblatt, F. (1959), “Two theorems of statistical separability in the perceptron,” Mechani-
zation of Thought Processes, Symposium held at the National Physical Laboratory,
HM Stationary Office, pp. 421-456.
Shapiro, A.F. (2000) “A Hitchhiker’s Guide to the Techniques of Adaptive Nonlinear Mod-
els," Insurance: Mathematics and Economics 26, pp. 119-132.
Shapiro, A. F., J. S. Pflumm and T. A. DeFilippo. (1999) “The Inner Workings of Neural
Networks and Genetic Algorithms,” ARCH, 1999 Vol. 1, 415-426.
Sharpe, W. F. (1975) "Likely Gains from Market Timing," Financial Analysts Journal,
March/April, pp. 60-69.
Surkan, A. J. and X. Ying. (1991) “Bond Rating Formulas Derived Through Simplifying a
Trained Neural Network.” IEEE International Joint Conference on Neural
Networks 2, 1566-1570. 18-21 November.
Tan, C. N. W. (1997) “An Artificial Neural Networks Primer with Financial Applications
Examples in Financial Distress Predictions and Foreign Exchange Hybrid Trading
System.”
Tansel, I. N., S. Y. Yang, g. Venkataraman, A. Sasirathsiri, W. Y. Bao and N. Mahendrakar.
(1999) “Modeling Time Series Data by Using Neural Netwroks and Genetic Algo-
rithms.” In in Dagli, C. H., A. L. Buczak, J. Ghosh, M. J. Embrechts, and O. Ersoy
(Eds.) Smart Engineering System Design: neural networks, fuzzy logic, evolutionary
programming, data mining, and complex systems. Proceedings of the Artificial Neural
Networks in Engineering Conference (ANNIE '99). New York: ASME Press, 1055-
1060.
Thammano, A. (1999) "Neuro-fuzzy Model for Stock Market Prediction," in Dagli, C. H., A.
L. Buczak, J. Ghosh, M. J. Embrechts, and O. Ersoy (Eds.) Smart Engineering Sys-
tem Design: neural networks, fuzzy logic, evolutionary programming, data mining,
and complex systems. Proceedings of the Artificial Neural Networks in Engineering
Conference (ANNIE '99). New York: ASME Press, pp. 587-591.
AFIR 2003_Shapiro_19.pdf 18
19. Thomas, B. (1996) Evolutionary Algorithms in Theory and Practice: Evolution Strategies,
Evolutionary Programming, Genetic Algorithms, Oxford University Press.
Trafalis, T. B. (1999) "Artificial Neural Networks Applied to Financial Forecasting,” in
Dagli, C. H., A. L. Buczak, J. Ghosh, M. J. Embrechts, and O. Ersoy (Eds.) Smart
Engineering Systems: Neural Networks, Fuzzy Logic, Data Mining, and
Evolutionary Programming, Proceedings of the Artificial Neural Networks in
Engineering Conference (ANNIE'99). New York: ASME Press, 1049-1054.
Tsaih, R. (1999) “Sensitivity Analysis, Neural Networks, and the Finance.” IEEE Interna-
tional Joint Conference on Neural Networks 6, 3830-3835.
Wendt, R. Q. (1995) “Build Your own GA Efficient Frontier.” Risks and Rewards, Decem-
ber: 1, (24) 4-5.
White, H. (1988) "Economic Prediction Using Neural Networks: The Case of IBM Daily
Stock Returns" in Proceedings of the Second Annual IEEE Conference on Neural
Networks, II: 451-458
Widrow, B. and Hoff, M.E. (1960), “Adaptive switching circuits” IRE Western Electric
Show and Convention Record, Part 4, August, pp. 96-104.
Wilson, C. L. (1994) “Self-Organizing Neural Network System for Trading Common
Stocks.” IEEE International Conference on Neural Networks 6, 3651-3654. 27 June-
2 July.
Yao, J., Y. Li, C. L. Tan. (2000) “Option Price Forecasting Using Neural Networks.” Omega,
The International Journal of Management Science, 28 (2000) 455-466.
Zadeh, L.A. (1965) "Fuzzy Sets," Information and Control, Vol. 8, pp.338-353.
Zadeh, L. A. (1992) Foreword of the Proceedings of the Second International Conference on
Fuzzy Logic and Neural Networks, xiii-xiv, Iizuka, Japan.10
AFIR 2003_Shapiro_19.pdf 19
20. Endnotes
1
Readers not familiar with neural networks, fuzzy logic or genetic algorithms can find a simple overview of the
technical details of these technologies in Shapiro (2000). A working knowledge of these technologies can be
obtained by reading Francis (2001) and Brockett et al. (1998) for neural networks, Ostaszewski (1993) for
fuzzy logic, and Shapiro et al. (1999) and Wendt (1995) for genetic algorithms.
2
Following Zadeh (1994, p. 192), in this article the term fuzzy logic is used in the broad sense where it is essentially
synonymous with fuzzy set theory.
3
All the FL studies reviewed in this article use some form of the FIS, so that is all that is reviewed in this section. It is
important to mention, however, that FISs cannot adapt or learn because they are unable to extract knowledge from
existing data and, where this is an issue, a fuzzy clustering method such as the fuzzy c-means algorithm (Bezdek
1981) is often used. The essence of the c-means algorithm is that it produces reasonable centers for clusters of data, in
the sense that the centers capture the essential feature of the cluster, and then groups data vectors around cluster cen-
ters that are reasonably close to them. The net result is that the within clusters variances are minimized and the be-
tween clusters variances are maximized.
4
The numerical input can be crisp or fuzzy. In this latter event, the input does not have to be fuzzified.
5
GAs are a subset of the broader category of Evolutionary Computing (EC), which is comprised of the evolutionary
optimization methods that work by simulating evolution on a computer. The three main subcategories of EC are Ge-
netic Algorithms (GAs), Evolutionary Programming (EP) and Evolution Strategy (ES) (Thomas (1996). GAs are the
most commonly used.
6
Kassicieh et. al. (1998, p. 122) and Farmer and Lo (1999, p. 9991).
7
The two main methods for estimating volatility are the historical volatility and the implied volatility. Histori-
cal volatility is the annualized standard deviation of historical rates of daily return and is estimate from a sample
of past prices of the underlying asset. Implied volatility is obtained by solving the Black-Scholes option pricing
model for the volatility that yields the observed call price, and is the standard method of estimating volatility at
the moment of trading.
8
The Box-Cox transformation is useful when the relationship between the variables lacks normality or has a
non-constant variance.
9
Monotonicity analysis measures the extent to which the relationship between the output of the NN and each
input variable is monotonic.
AFIR 2003_Shapiro_19.pdf 20