SlideShare a Scribd company logo
White Paper
Artificial Intelligence in Finance
http://streamdata.io
Prepared by:
Theodore Marrinan
& Kin Lane
tmarrinan@gmail.com
kinlane@gmail.com
Computer scientist John McCarthy was the first to
coin the phrase artificial intelligence (AI) in 1956
at Dartmouth College while organizing a conference
to examine how machines could be made to
simulate aspects of human intelligence. Since that
foundational conference, AI has developed into an
integral part of daily modern life and transformed
our economy. From internet search engines to
autonomous vehicles, AI has rapidly evolved
into a critical modern technology with extensive
applications in numerous fields. According to the
Harvard Business Review, AI has become “the
most important general-purpose technology of our
era”. AI leverages computers’ intrinsic advantages
over humans like speed, accuracy, and memory
storage. Accordingly, implementing AI can make
many processes more efficient and effective for both
businesses and researchers alike.
Forms of Artificial Intelligence (AI)
•	 Artificial Intelligence is a diverse field that aims
to enable computers to mimic aspects of human
intelligence.
•	 Machine Learning is a form of AI that teaches
itself and learns from provided data sets.
•	 Deep Learning is a form of ML that uses multiple
levels of abstraction to form a hierarchy of
concepts.
•	 Supervised Learning is a form of ML that uses
labeled training data where respective inputs and
outputs are paired together.
•	 Unsupervised Learning is a form of ML that uses
unlabeled training data where no categorization
of the data is provided.
•	 Semi-supervised Learning is a hybrid form of ML
that uses a combination of labeled and unlabeled
training data.
Within the field ofAI, the majority of recent research
and development efforts have primarily focused on
Artificial Intelligence has had a transformative impact on the modern economy. Technologies like machine learning,
deep learning, and neural networks are being combined with cloud computing, open source software tools, and big
data to power unprecedented breakthroughs in AI and revolutionize Finance. From compliance to traders, AI is being
used across the industry to automate repetitive tasks, improve efficiency, and augment human decision making.
artificially intelligent programs that can learn and
teach themselves to adapt to data called Machine
Learning (ML). ML uses a variety of algorithms to
parse data, learn from it, and determine or predict
some characteristic or value. Thanks to advances in
computing and the Big Data movement, powerful
ML algorithms can now parse vast new data sets and
generate unprecedented insights for businesses and
researchers. ML techniques have powered some of
the greatest breakthroughs in the field ofAI, and their
broad applicability has led to widespread adoption.
ML saves both time and money, as previously mind-
numbing tasks can now increasingly be automated,
freeing up human talent for higher level work with
greater added value. ML techniques are generally
most effective when there are large historical data
sets available for training the algorithms.
Training is a term used to describe the initial
optimization of general ML techniques for specific
applications. Algorithms are “trained” as they
analyze and learn from a provided training data
set. Once they are trained, algorithms can use what
they learned to analyze new, previously unforeseen
data. Training is a critical process for effective
ML, as it forms the basis for how the algorithms
actually function. Training can entail supervised,
semi-supervised, or unsupervised learning methods
depending on the type of training data provided and
the ML algorithm used.
There are also several factors to consider when
choosing between supervised and unsupervised ML
methods. Oftentimes, the structure and quantity
of available training data will dictate which kind
of algorithm is selected. In general, supervised
learning methods will normally require more effort
to set up than unsupervised methods, as all of the
training data must first be accurately labeled before
any training can start. Labeling training data can
be time-consuming, particularly if the data set is
large or complex, but it can provide some important
benefits. Namely, labeling specific input and
output pairs can create a structure for the data that
algorithms can then learn. Knowing the structure of
data can greatly improve the accuracy of algorithms’
Artificial Intelligence in Finance
predictions or classifications, so long as the labeled
structure is actually an accurate representation of the
real structure. Conversely, if there is no previously
knowndatastructure,unsupervisedlearningmayhelp
generate new insights into the data. Unsupervised
learning methods can therefore often be particularly
helpful when one is analyzing massive data sets that
are too large to be labeled. Some ML algorithms,
like the Naïve Bayes Classifier, are particularly
useful in applications where there is little training
data available and a fast approximation is required.
Other ML algorithms, like Neural Networks, excel
in applications where there are vast amounts of data
that can be used for training.
Currently, most practical ML applications utilize
supervised learning methods. Supervised learning is
popular because labeling can be a way to represent
data’s underlying structure in a form algorithms can
easily understand. This structural information can
help improve ML algorithms accuracy and greatly
reduce the amount of time needed for training. As
the amount of data produced by modern society
has continued to grow at an exponential pace and
unlabeled data is generally more abundant than
labeled data, semi-supervised and unsupervised
learning methods are increasingly thought to be the
future of ML.
When training ML algorithms, there are a number
of important elements one must consider. Firstly, it
is important to have some understanding of the level
of complexity possessed by the underlying function
that the ML algorithm is attempting to learn. If the
underlying function is complex, it will be necessary
to use very large training data sets and a more
flexible learning algorithm like a neural network.
In general, the more training data that is available
the better. Another important consideration is the
available training data’s quality. If the data is very
noisy or contains a lot of redundant information,
ML algorithms will generally perform poorly. After
training, it is also very important to test the accuracy
of algorithms with new data points that were not
used for training to help detect overfitting. When an
algorithm’sperformanceismaximizedforsomesetof
training data, it can often follow the specific training
data too closely instead of actually approximating
the underlying model structure. This is a problem
known as overfitting, and it causes algorithms to
have higher error rates when presented with new
data points. Testing algorithms with new data can
also provide important information regarding the
accuracy of their classifications or predictions.
Often as time marches on and new data points are
created, the underlying model that a ML algorithm
is trying to approximate can shift and change.
For example, if you trained a ML algorithm using
data from a bullish period in the stock market, the
resulting algorithm would likely perform well when
there is a bull market. However, if the economy were
to go into a recession and the stock market shifted to
a bearish period, the algorithm trained on a bullish
period would likely not perform as well, since the
underlying model has changed from a bull market
to a bear market. This concept drift occurs when
the statistical properties of a target variable change
over time, and it is an unavoidable part of modelling
complex phenomenon.
There are two main methods for adjusting for
inevitableconceptdrifts.Thefirstisanactivesolution
that relies on a triggering mechanism like a change-
detection test. This method is a form of statistical
analysisthatseekstoexplicitlyidentifywhenconcept
driftoccurssothatanew,moreaccuratemodelmaybe
implemented. The second method is a more passive
solution that focuses on retraining models using the
most recently received data, thereby continuously
updating it. Econometrically speaking, concept drift
is often the result of unobserved contextual data,
like seasonality or the business cycle. By adding in
useful additional data, it may be possible to greatly
reduce the deterioration in model performance
caused by concept drift. For example, if a model
used macroeconomic data to predict consumer sales
and its performance declines due to concept drift, the
model’s performance could possibly be bolstered by
adding seasonal data into the model. By helping to
contextualize trends like holiday shopping, concept
drift’s negative effects could potentially be reduced,
or even eliminated. While contextual data may
help to reduce some instances of concept drift, not
all trends can necessarily be easily contextualized
through additional data, and new factors may arise
or known factors may change at any time. Despite
these limitations, adding new contextual data to
models can still help to minimize concept drift’s
harmful effects on performance, particularly if a
second adjustment method like continuous retraining
is also used.
ML has developed a number of highly capable and
powerful techniques over the years that are used for a
widearrayofdifferentapplications.Whilestilllargely
basedonprobabilitytheoryandstatisticaltechniques,
ML has also come to incorporate concepts from a

More Related Content

Recently uploaded

一比一原版(LBS毕业证)伦敦商学院毕业证成绩单专业办理
一比一原版(LBS毕业证)伦敦商学院毕业证成绩单专业办理一比一原版(LBS毕业证)伦敦商学院毕业证成绩单专业办理
一比一原版(LBS毕业证)伦敦商学院毕业证成绩单专业办理
eutxy
 
APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024
APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024
APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024
APNIC
 
Bridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptx
Bridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptxBridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptx
Bridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptx
Brad Spiegel Macon GA
 
Comptia N+ Standard Networking lesson guide
Comptia N+ Standard Networking lesson guideComptia N+ Standard Networking lesson guide
Comptia N+ Standard Networking lesson guide
GTProductions1
 
1.Wireless Communication System_Wireless communication is a broad term that i...
1.Wireless Communication System_Wireless communication is a broad term that i...1.Wireless Communication System_Wireless communication is a broad term that i...
1.Wireless Communication System_Wireless communication is a broad term that i...
JeyaPerumal1
 
原版仿制(uob毕业证书)英国伯明翰大学毕业证本科学历证书原版一模一样
原版仿制(uob毕业证书)英国伯明翰大学毕业证本科学历证书原版一模一样原版仿制(uob毕业证书)英国伯明翰大学毕业证本科学历证书原版一模一样
原版仿制(uob毕业证书)英国伯明翰大学毕业证本科学历证书原版一模一样
3ipehhoa
 
一比一原版(SLU毕业证)圣路易斯大学毕业证成绩单专业办理
一比一原版(SLU毕业证)圣路易斯大学毕业证成绩单专业办理一比一原版(SLU毕业证)圣路易斯大学毕业证成绩单专业办理
一比一原版(SLU毕业证)圣路易斯大学毕业证成绩单专业办理
keoku
 
How to Use Contact Form 7 Like a Pro.pptx
How to Use Contact Form 7 Like a Pro.pptxHow to Use Contact Form 7 Like a Pro.pptx
How to Use Contact Form 7 Like a Pro.pptx
Gal Baras
 
BASIC C++ lecture NOTE C++ lecture 3.pptx
BASIC C++ lecture NOTE C++ lecture 3.pptxBASIC C++ lecture NOTE C++ lecture 3.pptx
BASIC C++ lecture NOTE C++ lecture 3.pptx
natyesu
 
JAVIER LASA-EXPERIENCIA digital 1986-2024.pdf
JAVIER LASA-EXPERIENCIA digital 1986-2024.pdfJAVIER LASA-EXPERIENCIA digital 1986-2024.pdf
JAVIER LASA-EXPERIENCIA digital 1986-2024.pdf
Javier Lasa
 
急速办(bedfordhire毕业证书)英国贝德福特大学毕业证成绩单原版一模一样
急速办(bedfordhire毕业证书)英国贝德福特大学毕业证成绩单原版一模一样急速办(bedfordhire毕业证书)英国贝德福特大学毕业证成绩单原版一模一样
急速办(bedfordhire毕业证书)英国贝德福特大学毕业证成绩单原版一模一样
3ipehhoa
 
The+Prospects+of+E-Commerce+in+China.pptx
The+Prospects+of+E-Commerce+in+China.pptxThe+Prospects+of+E-Commerce+in+China.pptx
The+Prospects+of+E-Commerce+in+China.pptx
laozhuseo02
 
一比一原版(CSU毕业证)加利福尼亚州立大学毕业证成绩单专业办理
一比一原版(CSU毕业证)加利福尼亚州立大学毕业证成绩单专业办理一比一原版(CSU毕业证)加利福尼亚州立大学毕业证成绩单专业办理
一比一原版(CSU毕业证)加利福尼亚州立大学毕业证成绩单专业办理
ufdana
 
1比1复刻(bath毕业证书)英国巴斯大学毕业证学位证原版一模一样
1比1复刻(bath毕业证书)英国巴斯大学毕业证学位证原版一模一样1比1复刻(bath毕业证书)英国巴斯大学毕业证学位证原版一模一样
1比1复刻(bath毕业证书)英国巴斯大学毕业证学位证原版一模一样
3ipehhoa
 
Internet-Security-Safeguarding-Your-Digital-World (1).pptx
Internet-Security-Safeguarding-Your-Digital-World (1).pptxInternet-Security-Safeguarding-Your-Digital-World (1).pptx
Internet-Security-Safeguarding-Your-Digital-World (1).pptx
VivekSinghShekhawat2
 
Latest trends in computer networking.pptx
Latest trends in computer networking.pptxLatest trends in computer networking.pptx
Latest trends in computer networking.pptx
JungkooksNonexistent
 
guildmasters guide to ravnica Dungeons & Dragons 5...
guildmasters guide to ravnica Dungeons & Dragons 5...guildmasters guide to ravnica Dungeons & Dragons 5...
guildmasters guide to ravnica Dungeons & Dragons 5...
Rogerio Filho
 
This 7-second Brain Wave Ritual Attracts Money To You.!
This 7-second Brain Wave Ritual Attracts Money To You.!This 7-second Brain Wave Ritual Attracts Money To You.!
This 7-second Brain Wave Ritual Attracts Money To You.!
nirahealhty
 
test test test test testtest test testtest test testtest test testtest test ...
test test  test test testtest test testtest test testtest test testtest test ...test test  test test testtest test testtest test testtest test testtest test ...
test test test test testtest test testtest test testtest test testtest test ...
Arif0071
 
Multi-cluster Kubernetes Networking- Patterns, Projects and Guidelines
Multi-cluster Kubernetes Networking- Patterns, Projects and GuidelinesMulti-cluster Kubernetes Networking- Patterns, Projects and Guidelines
Multi-cluster Kubernetes Networking- Patterns, Projects and Guidelines
Sanjeev Rampal
 

Recently uploaded (20)

一比一原版(LBS毕业证)伦敦商学院毕业证成绩单专业办理
一比一原版(LBS毕业证)伦敦商学院毕业证成绩单专业办理一比一原版(LBS毕业证)伦敦商学院毕业证成绩单专业办理
一比一原版(LBS毕业证)伦敦商学院毕业证成绩单专业办理
 
APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024
APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024
APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024
 
Bridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptx
Bridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptxBridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptx
Bridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptx
 
Comptia N+ Standard Networking lesson guide
Comptia N+ Standard Networking lesson guideComptia N+ Standard Networking lesson guide
Comptia N+ Standard Networking lesson guide
 
1.Wireless Communication System_Wireless communication is a broad term that i...
1.Wireless Communication System_Wireless communication is a broad term that i...1.Wireless Communication System_Wireless communication is a broad term that i...
1.Wireless Communication System_Wireless communication is a broad term that i...
 
原版仿制(uob毕业证书)英国伯明翰大学毕业证本科学历证书原版一模一样
原版仿制(uob毕业证书)英国伯明翰大学毕业证本科学历证书原版一模一样原版仿制(uob毕业证书)英国伯明翰大学毕业证本科学历证书原版一模一样
原版仿制(uob毕业证书)英国伯明翰大学毕业证本科学历证书原版一模一样
 
一比一原版(SLU毕业证)圣路易斯大学毕业证成绩单专业办理
一比一原版(SLU毕业证)圣路易斯大学毕业证成绩单专业办理一比一原版(SLU毕业证)圣路易斯大学毕业证成绩单专业办理
一比一原版(SLU毕业证)圣路易斯大学毕业证成绩单专业办理
 
How to Use Contact Form 7 Like a Pro.pptx
How to Use Contact Form 7 Like a Pro.pptxHow to Use Contact Form 7 Like a Pro.pptx
How to Use Contact Form 7 Like a Pro.pptx
 
BASIC C++ lecture NOTE C++ lecture 3.pptx
BASIC C++ lecture NOTE C++ lecture 3.pptxBASIC C++ lecture NOTE C++ lecture 3.pptx
BASIC C++ lecture NOTE C++ lecture 3.pptx
 
JAVIER LASA-EXPERIENCIA digital 1986-2024.pdf
JAVIER LASA-EXPERIENCIA digital 1986-2024.pdfJAVIER LASA-EXPERIENCIA digital 1986-2024.pdf
JAVIER LASA-EXPERIENCIA digital 1986-2024.pdf
 
急速办(bedfordhire毕业证书)英国贝德福特大学毕业证成绩单原版一模一样
急速办(bedfordhire毕业证书)英国贝德福特大学毕业证成绩单原版一模一样急速办(bedfordhire毕业证书)英国贝德福特大学毕业证成绩单原版一模一样
急速办(bedfordhire毕业证书)英国贝德福特大学毕业证成绩单原版一模一样
 
The+Prospects+of+E-Commerce+in+China.pptx
The+Prospects+of+E-Commerce+in+China.pptxThe+Prospects+of+E-Commerce+in+China.pptx
The+Prospects+of+E-Commerce+in+China.pptx
 
一比一原版(CSU毕业证)加利福尼亚州立大学毕业证成绩单专业办理
一比一原版(CSU毕业证)加利福尼亚州立大学毕业证成绩单专业办理一比一原版(CSU毕业证)加利福尼亚州立大学毕业证成绩单专业办理
一比一原版(CSU毕业证)加利福尼亚州立大学毕业证成绩单专业办理
 
1比1复刻(bath毕业证书)英国巴斯大学毕业证学位证原版一模一样
1比1复刻(bath毕业证书)英国巴斯大学毕业证学位证原版一模一样1比1复刻(bath毕业证书)英国巴斯大学毕业证学位证原版一模一样
1比1复刻(bath毕业证书)英国巴斯大学毕业证学位证原版一模一样
 
Internet-Security-Safeguarding-Your-Digital-World (1).pptx
Internet-Security-Safeguarding-Your-Digital-World (1).pptxInternet-Security-Safeguarding-Your-Digital-World (1).pptx
Internet-Security-Safeguarding-Your-Digital-World (1).pptx
 
Latest trends in computer networking.pptx
Latest trends in computer networking.pptxLatest trends in computer networking.pptx
Latest trends in computer networking.pptx
 
guildmasters guide to ravnica Dungeons & Dragons 5...
guildmasters guide to ravnica Dungeons & Dragons 5...guildmasters guide to ravnica Dungeons & Dragons 5...
guildmasters guide to ravnica Dungeons & Dragons 5...
 
This 7-second Brain Wave Ritual Attracts Money To You.!
This 7-second Brain Wave Ritual Attracts Money To You.!This 7-second Brain Wave Ritual Attracts Money To You.!
This 7-second Brain Wave Ritual Attracts Money To You.!
 
test test test test testtest test testtest test testtest test testtest test ...
test test  test test testtest test testtest test testtest test testtest test ...test test  test test testtest test testtest test testtest test testtest test ...
test test test test testtest test testtest test testtest test testtest test ...
 
Multi-cluster Kubernetes Networking- Patterns, Projects and Guidelines
Multi-cluster Kubernetes Networking- Patterns, Projects and GuidelinesMulti-cluster Kubernetes Networking- Patterns, Projects and Guidelines
Multi-cluster Kubernetes Networking- Patterns, Projects and Guidelines
 

Featured

2024 State of Marketing Report – by Hubspot
2024 State of Marketing Report – by Hubspot2024 State of Marketing Report – by Hubspot
2024 State of Marketing Report – by Hubspot
Marius Sescu
 
Everything You Need To Know About ChatGPT
Everything You Need To Know About ChatGPTEverything You Need To Know About ChatGPT
Everything You Need To Know About ChatGPT
Expeed Software
 
Product Design Trends in 2024 | Teenage Engineerings
Product Design Trends in 2024 | Teenage EngineeringsProduct Design Trends in 2024 | Teenage Engineerings
Product Design Trends in 2024 | Teenage Engineerings
Pixeldarts
 
How Race, Age and Gender Shape Attitudes Towards Mental Health
How Race, Age and Gender Shape Attitudes Towards Mental HealthHow Race, Age and Gender Shape Attitudes Towards Mental Health
How Race, Age and Gender Shape Attitudes Towards Mental Health
ThinkNow
 
AI Trends in Creative Operations 2024 by Artwork Flow.pdf
AI Trends in Creative Operations 2024 by Artwork Flow.pdfAI Trends in Creative Operations 2024 by Artwork Flow.pdf
AI Trends in Creative Operations 2024 by Artwork Flow.pdf
marketingartwork
 
Skeleton Culture Code
Skeleton Culture CodeSkeleton Culture Code
Skeleton Culture Code
Skeleton Technologies
 
PEPSICO Presentation to CAGNY Conference Feb 2024
PEPSICO Presentation to CAGNY Conference Feb 2024PEPSICO Presentation to CAGNY Conference Feb 2024
PEPSICO Presentation to CAGNY Conference Feb 2024
Neil Kimberley
 
Content Methodology: A Best Practices Report (Webinar)
Content Methodology: A Best Practices Report (Webinar)Content Methodology: A Best Practices Report (Webinar)
Content Methodology: A Best Practices Report (Webinar)
contently
 
How to Prepare For a Successful Job Search for 2024
How to Prepare For a Successful Job Search for 2024How to Prepare For a Successful Job Search for 2024
How to Prepare For a Successful Job Search for 2024
Albert Qian
 
Social Media Marketing Trends 2024 // The Global Indie Insights
Social Media Marketing Trends 2024 // The Global Indie InsightsSocial Media Marketing Trends 2024 // The Global Indie Insights
Social Media Marketing Trends 2024 // The Global Indie Insights
Kurio // The Social Media Age(ncy)
 
Trends In Paid Search: Navigating The Digital Landscape In 2024
Trends In Paid Search: Navigating The Digital Landscape In 2024Trends In Paid Search: Navigating The Digital Landscape In 2024
Trends In Paid Search: Navigating The Digital Landscape In 2024
Search Engine Journal
 
5 Public speaking tips from TED - Visualized summary
5 Public speaking tips from TED - Visualized summary5 Public speaking tips from TED - Visualized summary
5 Public speaking tips from TED - Visualized summary
SpeakerHub
 
ChatGPT and the Future of Work - Clark Boyd
ChatGPT and the Future of Work - Clark Boyd ChatGPT and the Future of Work - Clark Boyd
ChatGPT and the Future of Work - Clark Boyd
Clark Boyd
 
Getting into the tech field. what next
Getting into the tech field. what next Getting into the tech field. what next
Getting into the tech field. what next
Tessa Mero
 
Google's Just Not That Into You: Understanding Core Updates & Search Intent
Google's Just Not That Into You: Understanding Core Updates & Search IntentGoogle's Just Not That Into You: Understanding Core Updates & Search Intent
Google's Just Not That Into You: Understanding Core Updates & Search Intent
Lily Ray
 
How to have difficult conversations
How to have difficult conversations How to have difficult conversations
How to have difficult conversations
Rajiv Jayarajah, MAppComm, ACC
 
Introduction to Data Science
Introduction to Data ScienceIntroduction to Data Science
Introduction to Data Science
Christy Abraham Joy
 
Time Management & Productivity - Best Practices
Time Management & Productivity -  Best PracticesTime Management & Productivity -  Best Practices
Time Management & Productivity - Best Practices
Vit Horky
 
The six step guide to practical project management
The six step guide to practical project managementThe six step guide to practical project management
The six step guide to practical project management
MindGenius
 
Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...
Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...
Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...
RachelPearson36
 

Featured (20)

2024 State of Marketing Report – by Hubspot
2024 State of Marketing Report – by Hubspot2024 State of Marketing Report – by Hubspot
2024 State of Marketing Report – by Hubspot
 
Everything You Need To Know About ChatGPT
Everything You Need To Know About ChatGPTEverything You Need To Know About ChatGPT
Everything You Need To Know About ChatGPT
 
Product Design Trends in 2024 | Teenage Engineerings
Product Design Trends in 2024 | Teenage EngineeringsProduct Design Trends in 2024 | Teenage Engineerings
Product Design Trends in 2024 | Teenage Engineerings
 
How Race, Age and Gender Shape Attitudes Towards Mental Health
How Race, Age and Gender Shape Attitudes Towards Mental HealthHow Race, Age and Gender Shape Attitudes Towards Mental Health
How Race, Age and Gender Shape Attitudes Towards Mental Health
 
AI Trends in Creative Operations 2024 by Artwork Flow.pdf
AI Trends in Creative Operations 2024 by Artwork Flow.pdfAI Trends in Creative Operations 2024 by Artwork Flow.pdf
AI Trends in Creative Operations 2024 by Artwork Flow.pdf
 
Skeleton Culture Code
Skeleton Culture CodeSkeleton Culture Code
Skeleton Culture Code
 
PEPSICO Presentation to CAGNY Conference Feb 2024
PEPSICO Presentation to CAGNY Conference Feb 2024PEPSICO Presentation to CAGNY Conference Feb 2024
PEPSICO Presentation to CAGNY Conference Feb 2024
 
Content Methodology: A Best Practices Report (Webinar)
Content Methodology: A Best Practices Report (Webinar)Content Methodology: A Best Practices Report (Webinar)
Content Methodology: A Best Practices Report (Webinar)
 
How to Prepare For a Successful Job Search for 2024
How to Prepare For a Successful Job Search for 2024How to Prepare For a Successful Job Search for 2024
How to Prepare For a Successful Job Search for 2024
 
Social Media Marketing Trends 2024 // The Global Indie Insights
Social Media Marketing Trends 2024 // The Global Indie InsightsSocial Media Marketing Trends 2024 // The Global Indie Insights
Social Media Marketing Trends 2024 // The Global Indie Insights
 
Trends In Paid Search: Navigating The Digital Landscape In 2024
Trends In Paid Search: Navigating The Digital Landscape In 2024Trends In Paid Search: Navigating The Digital Landscape In 2024
Trends In Paid Search: Navigating The Digital Landscape In 2024
 
5 Public speaking tips from TED - Visualized summary
5 Public speaking tips from TED - Visualized summary5 Public speaking tips from TED - Visualized summary
5 Public speaking tips from TED - Visualized summary
 
ChatGPT and the Future of Work - Clark Boyd
ChatGPT and the Future of Work - Clark Boyd ChatGPT and the Future of Work - Clark Boyd
ChatGPT and the Future of Work - Clark Boyd
 
Getting into the tech field. what next
Getting into the tech field. what next Getting into the tech field. what next
Getting into the tech field. what next
 
Google's Just Not That Into You: Understanding Core Updates & Search Intent
Google's Just Not That Into You: Understanding Core Updates & Search IntentGoogle's Just Not That Into You: Understanding Core Updates & Search Intent
Google's Just Not That Into You: Understanding Core Updates & Search Intent
 
How to have difficult conversations
How to have difficult conversations How to have difficult conversations
How to have difficult conversations
 
Introduction to Data Science
Introduction to Data ScienceIntroduction to Data Science
Introduction to Data Science
 
Time Management & Productivity - Best Practices
Time Management & Productivity -  Best PracticesTime Management & Productivity -  Best Practices
Time Management & Productivity - Best Practices
 
The six step guide to practical project management
The six step guide to practical project managementThe six step guide to practical project management
The six step guide to practical project management
 
Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...
Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...
Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...
 

Artificial Intelligence in Finance

  • 1. White Paper Artificial Intelligence in Finance http://streamdata.io Prepared by: Theodore Marrinan & Kin Lane tmarrinan@gmail.com kinlane@gmail.com
  • 2. Computer scientist John McCarthy was the first to coin the phrase artificial intelligence (AI) in 1956 at Dartmouth College while organizing a conference to examine how machines could be made to simulate aspects of human intelligence. Since that foundational conference, AI has developed into an integral part of daily modern life and transformed our economy. From internet search engines to autonomous vehicles, AI has rapidly evolved into a critical modern technology with extensive applications in numerous fields. According to the Harvard Business Review, AI has become “the most important general-purpose technology of our era”. AI leverages computers’ intrinsic advantages over humans like speed, accuracy, and memory storage. Accordingly, implementing AI can make many processes more efficient and effective for both businesses and researchers alike. Forms of Artificial Intelligence (AI) • Artificial Intelligence is a diverse field that aims to enable computers to mimic aspects of human intelligence. • Machine Learning is a form of AI that teaches itself and learns from provided data sets. • Deep Learning is a form of ML that uses multiple levels of abstraction to form a hierarchy of concepts. • Supervised Learning is a form of ML that uses labeled training data where respective inputs and outputs are paired together. • Unsupervised Learning is a form of ML that uses unlabeled training data where no categorization of the data is provided. • Semi-supervised Learning is a hybrid form of ML that uses a combination of labeled and unlabeled training data. Within the field ofAI, the majority of recent research and development efforts have primarily focused on Artificial Intelligence has had a transformative impact on the modern economy. Technologies like machine learning, deep learning, and neural networks are being combined with cloud computing, open source software tools, and big data to power unprecedented breakthroughs in AI and revolutionize Finance. From compliance to traders, AI is being used across the industry to automate repetitive tasks, improve efficiency, and augment human decision making. artificially intelligent programs that can learn and teach themselves to adapt to data called Machine Learning (ML). ML uses a variety of algorithms to parse data, learn from it, and determine or predict some characteristic or value. Thanks to advances in computing and the Big Data movement, powerful ML algorithms can now parse vast new data sets and generate unprecedented insights for businesses and researchers. ML techniques have powered some of the greatest breakthroughs in the field ofAI, and their broad applicability has led to widespread adoption. ML saves both time and money, as previously mind- numbing tasks can now increasingly be automated, freeing up human talent for higher level work with greater added value. ML techniques are generally most effective when there are large historical data sets available for training the algorithms. Training is a term used to describe the initial optimization of general ML techniques for specific applications. Algorithms are “trained” as they analyze and learn from a provided training data set. Once they are trained, algorithms can use what they learned to analyze new, previously unforeseen data. Training is a critical process for effective ML, as it forms the basis for how the algorithms actually function. Training can entail supervised, semi-supervised, or unsupervised learning methods depending on the type of training data provided and the ML algorithm used. There are also several factors to consider when choosing between supervised and unsupervised ML methods. Oftentimes, the structure and quantity of available training data will dictate which kind of algorithm is selected. In general, supervised learning methods will normally require more effort to set up than unsupervised methods, as all of the training data must first be accurately labeled before any training can start. Labeling training data can be time-consuming, particularly if the data set is large or complex, but it can provide some important benefits. Namely, labeling specific input and output pairs can create a structure for the data that algorithms can then learn. Knowing the structure of data can greatly improve the accuracy of algorithms’ Artificial Intelligence in Finance
  • 3. predictions or classifications, so long as the labeled structure is actually an accurate representation of the real structure. Conversely, if there is no previously knowndatastructure,unsupervisedlearningmayhelp generate new insights into the data. Unsupervised learning methods can therefore often be particularly helpful when one is analyzing massive data sets that are too large to be labeled. Some ML algorithms, like the Naïve Bayes Classifier, are particularly useful in applications where there is little training data available and a fast approximation is required. Other ML algorithms, like Neural Networks, excel in applications where there are vast amounts of data that can be used for training. Currently, most practical ML applications utilize supervised learning methods. Supervised learning is popular because labeling can be a way to represent data’s underlying structure in a form algorithms can easily understand. This structural information can help improve ML algorithms accuracy and greatly reduce the amount of time needed for training. As the amount of data produced by modern society has continued to grow at an exponential pace and unlabeled data is generally more abundant than labeled data, semi-supervised and unsupervised learning methods are increasingly thought to be the future of ML. When training ML algorithms, there are a number of important elements one must consider. Firstly, it is important to have some understanding of the level of complexity possessed by the underlying function that the ML algorithm is attempting to learn. If the underlying function is complex, it will be necessary to use very large training data sets and a more flexible learning algorithm like a neural network. In general, the more training data that is available the better. Another important consideration is the available training data’s quality. If the data is very noisy or contains a lot of redundant information, ML algorithms will generally perform poorly. After training, it is also very important to test the accuracy of algorithms with new data points that were not used for training to help detect overfitting. When an algorithm’sperformanceismaximizedforsomesetof training data, it can often follow the specific training data too closely instead of actually approximating the underlying model structure. This is a problem known as overfitting, and it causes algorithms to have higher error rates when presented with new data points. Testing algorithms with new data can also provide important information regarding the accuracy of their classifications or predictions. Often as time marches on and new data points are created, the underlying model that a ML algorithm is trying to approximate can shift and change. For example, if you trained a ML algorithm using data from a bullish period in the stock market, the resulting algorithm would likely perform well when there is a bull market. However, if the economy were to go into a recession and the stock market shifted to a bearish period, the algorithm trained on a bullish period would likely not perform as well, since the underlying model has changed from a bull market to a bear market. This concept drift occurs when the statistical properties of a target variable change over time, and it is an unavoidable part of modelling complex phenomenon. There are two main methods for adjusting for inevitableconceptdrifts.Thefirstisanactivesolution that relies on a triggering mechanism like a change- detection test. This method is a form of statistical analysisthatseekstoexplicitlyidentifywhenconcept driftoccurssothatanew,moreaccuratemodelmaybe implemented. The second method is a more passive solution that focuses on retraining models using the most recently received data, thereby continuously updating it. Econometrically speaking, concept drift is often the result of unobserved contextual data, like seasonality or the business cycle. By adding in useful additional data, it may be possible to greatly reduce the deterioration in model performance caused by concept drift. For example, if a model used macroeconomic data to predict consumer sales and its performance declines due to concept drift, the model’s performance could possibly be bolstered by adding seasonal data into the model. By helping to contextualize trends like holiday shopping, concept drift’s negative effects could potentially be reduced, or even eliminated. While contextual data may help to reduce some instances of concept drift, not all trends can necessarily be easily contextualized through additional data, and new factors may arise or known factors may change at any time. Despite these limitations, adding new contextual data to models can still help to minimize concept drift’s harmful effects on performance, particularly if a second adjustment method like continuous retraining is also used. ML has developed a number of highly capable and powerful techniques over the years that are used for a widearrayofdifferentapplications.Whilestilllargely basedonprobabilitytheoryandstatisticaltechniques, ML has also come to incorporate concepts from a