Industry day keynote presentation held at ECIR 2016, Padova. The talk presents algorithmic, technical and business challenges Gravity R&D encountered from building a recommender system vendor company from being a top Netflix Prize contender.
Neighbor methods vs matrix factorization - case studies of real-life recommen...Domonkos Tikk
This talk was given by István Pilászy, co-founder and head of core development at Gravity R&D, at LSRS workshop at Recsys 2015. Messages of the talk: (1) in industry item-2-item (i2i) recommendation is the dominant case, hardly researched by academia; (2) in industry you have typically implicit feedback data; (3) matrix factorization (MF) is good to optimize error metric, but less obvious for top-N and i2i recommendations. (4) item-kNN in most cases outperforms MF for i2i in terms of CTR; (5) Performance heavily depends on the domain and the recommendation scenario.
Deep learning to the rescue - solving long standing problems of recommender ...Balázs Hidasi
I gave this talk at the 1st Budapest RecSys and Personalization Meetup about using deep learning to solve long standing problems of recommender systems. I also presented our approach on using RNNs for session-based recommendations in details.
Parallel Recurrent Neural Network Architectures for Feature-rich Session-base...Balázs Hidasi
Slides for my RecSys 2016 talk on integrating image and textual information into session based recommendations using novel parallel RNN architectures.
Link to the paper: http://www.hidasi.eu/en/publications.html#p_rnn_recsys16
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...Balázs Hidasi
Slides of my presentation at CIKM2018 about version 2 of the GRU4Rec algorithm, a recurrent neural network based algorithm for the session-based recommendation task.
We discuss sampling strategies and introduce additional sampling to the algorithm. We also redesign the loss function to cope with additional sampling. The resulting BPR-max loss function is able to efficiently handle many negative samples without encountering the vanishing gradient problem. We also introduce constrained embeddings which speeds up the conversion of item representations and reduces memory usage by a factor of 4. These improvements increase offline measures up to 52%.
In the talk we also discuss online A/B test and the implications of long time observations. Most of these observations are exclusive to this talk and are not in the paper.
You can access the preprint version of the paper on arXiv: https://arxiv.org/abs/1706.03847
The code is available on GitHub: https://github.com/hidasib/GRU4Rec
Deep Learning in Recommender Systems - RecSys Summer School 2017Balázs Hidasi
This is the presentation accompanying my tutorial about deep learning methods in the recommender systems domain. The tutorial consists of a brief general overview of deep learning and the introduction of the four most prominent research direction of DL in recsys as of 2017. Presented during RecSys Summer School 2017 in Bolzano, Italy.
Evolving a Medical Image Similarity SearchSujit Pal
Slides for talk at Haystack Conference 2018. Covers evolution of an Image Similarity Search Proof of Concept built to identify similar medical images. Discusses various image vectorizing techniques that were considered in order to convert images into searchable entities, an evaluation strategy to rank these techniques, as well as various indexing strategies to allow searching for similar images at scale.
Embed, Encode, Attend, Predict – applying the 4 step NLP recipe for text clas...Sujit Pal
Slides for talk at PyData Seattle 2017 about Matthew Honnibal's 4-step recipe for Deep Learning NLP pipelines. Description of the stages in pipeline as well as 3 examples of document classification, document similarity and sentence similarity. Examples include Keras custom layers for different types of attention.
Neighbor methods vs matrix factorization - case studies of real-life recommen...Domonkos Tikk
This talk was given by István Pilászy, co-founder and head of core development at Gravity R&D, at LSRS workshop at Recsys 2015. Messages of the talk: (1) in industry item-2-item (i2i) recommendation is the dominant case, hardly researched by academia; (2) in industry you have typically implicit feedback data; (3) matrix factorization (MF) is good to optimize error metric, but less obvious for top-N and i2i recommendations. (4) item-kNN in most cases outperforms MF for i2i in terms of CTR; (5) Performance heavily depends on the domain and the recommendation scenario.
Deep learning to the rescue - solving long standing problems of recommender ...Balázs Hidasi
I gave this talk at the 1st Budapest RecSys and Personalization Meetup about using deep learning to solve long standing problems of recommender systems. I also presented our approach on using RNNs for session-based recommendations in details.
Parallel Recurrent Neural Network Architectures for Feature-rich Session-base...Balázs Hidasi
Slides for my RecSys 2016 talk on integrating image and textual information into session based recommendations using novel parallel RNN architectures.
Link to the paper: http://www.hidasi.eu/en/publications.html#p_rnn_recsys16
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...Balázs Hidasi
Slides of my presentation at CIKM2018 about version 2 of the GRU4Rec algorithm, a recurrent neural network based algorithm for the session-based recommendation task.
We discuss sampling strategies and introduce additional sampling to the algorithm. We also redesign the loss function to cope with additional sampling. The resulting BPR-max loss function is able to efficiently handle many negative samples without encountering the vanishing gradient problem. We also introduce constrained embeddings which speeds up the conversion of item representations and reduces memory usage by a factor of 4. These improvements increase offline measures up to 52%.
In the talk we also discuss online A/B test and the implications of long time observations. Most of these observations are exclusive to this talk and are not in the paper.
You can access the preprint version of the paper on arXiv: https://arxiv.org/abs/1706.03847
The code is available on GitHub: https://github.com/hidasib/GRU4Rec
Deep Learning in Recommender Systems - RecSys Summer School 2017Balázs Hidasi
This is the presentation accompanying my tutorial about deep learning methods in the recommender systems domain. The tutorial consists of a brief general overview of deep learning and the introduction of the four most prominent research direction of DL in recsys as of 2017. Presented during RecSys Summer School 2017 in Bolzano, Italy.
Evolving a Medical Image Similarity SearchSujit Pal
Slides for talk at Haystack Conference 2018. Covers evolution of an Image Similarity Search Proof of Concept built to identify similar medical images. Discusses various image vectorizing techniques that were considered in order to convert images into searchable entities, an evaluation strategy to rank these techniques, as well as various indexing strategies to allow searching for similar images at scale.
Embed, Encode, Attend, Predict – applying the 4 step NLP recipe for text clas...Sujit Pal
Slides for talk at PyData Seattle 2017 about Matthew Honnibal's 4-step recipe for Deep Learning NLP pipelines. Description of the stages in pipeline as well as 3 examples of document classification, document similarity and sentence similarity. Examples include Keras custom layers for different types of attention.
Generative Adversarial Networks : Basic architecture and variantsananth
In this presentation we review the fundamentals behind GANs and look at different variants. We quickly review the theory such as the cost functions, training procedure, challenges and go on to look at variants such as CycleGAN, SAGAN etc.
Session-aware Linear Item-Item Models for Session-based Recommendation (WWW 2...민진 최
This is the official slide for the WWW 2021 paper: Session-aware Linear Item-Item Models for Session-based Recommendation
If you have any questions, please contact zxcvxd@skku.edu.
[GAN by Hung-yi Lee]Part 2: The application of GAN to speech and text processingNAVER Engineering
Generative Adversarial Network and its Applications on Speech and Natural Language Processing, Part 2.
발표자: Hung-yi Lee(국립 타이완대 교수)
발표일: 18.7.
Generative adversarial network (GAN) is a new idea for training models, in which a generator and a discriminator compete against each other to improve the generation quality. Recently, GAN has shown amazing results in image generation, and a large amount and a wide variety of new ideas, techniques, and applications have been developed based on it. Although there are only few successful cases, GAN has great potential to be applied to text and speech generations to overcome limitations in the conventional methods.
In the first part of the talk, I will first give an introduction of GAN and provide a thorough review about this technology. In the second part, I will focus on the applications of GAN to speech and natural language processing. I will demonstrate the applications of GAN on voice I will also talk about the research directions towards unsupervised speech recognition by GAN.conversion, unsupervised abstractive summarization and sentiment controllable chat-bot.
Ranking and Diversity in Recommendations - RecSys Stammtisch at SoundCloud, B...Alexandros Karatzoglou
Slides from my talk at the RecSys Stammtisch at SoundCloud in Berlin. The presentation is split in two part one focusing on ranking and relevance and one on diversity and how to achieve it using genres. We introduce a novel diversity metric called Binomial Diversity.
Tutorial on Deep Learning in Recommender System, Lars summer school 2019Anoop Deoras
I had a fun time giving tutorial on the topic of deep learning in recommender systems at Latin America School on Recommender Systems (LARS) in Fortaleza, Brazil.
Deep Learning with Python: Getting started and getting from ideas to insights in minutes.
PyData Seattle 2015
Alex Korbonits (@korbonits)
This presentation was given July 25, 2015 at the PyData Seattle conference hosted by PyData and NumFocus.
Machine Learning Essentials Demystified part1 | Big Data DemystifiedOmid Vahdaty
Machine Learning Essentials Abstract:
Machine Learning (ML) is one of the hottest topics in the IT world today. But what is it really all about?
In this session we will talk about what ML actually is and in which cases it is useful.
We will talk about a few common algorithms for creating ML models and demonstrate their use with Python. We will also take a peek at Deep Learning (DL) and Artificial Neural Networks and explain how they work (without too much math) and demonstrate DL model with Python.
The target audience are developers, data engineers and DBAs that do not have prior experience with ML and want to know how it actually works.
An overview of gradient descent optimization algorithms Hakky St
勾配降下法についての論文をスライドにしたものです。
This is the slide for study meeting of gradient descent.
I use this paper and this is very good information about gradient descent.
https://arxiv.org/abs/1609.04747
Deep learning: the future of recommendationsBalázs Hidasi
An informative talk about deep learning and its potential uses in recommender systems. Presented at the Budapest Startup Safary, 21 April, 2016.
The breakthroughs of the last decade in neural network research and the quick increasing of computational power resulted in the revival of deep neural networks and the field focusing on their training: deep learning. Deep learning methods have succeeded in complex tasks where other machine learning methods have failed, such as computer vision and natural language processing. Recently deep learning has began to gain ground in recommender systems as well. This talk introduces deep learning and its applications, with emphasis on how deep learning methods can solve long standing recommendation problems.
[GAN by Hung-yi Lee]Part 3: The recent research of my groupNAVER Engineering
Generative Adversarial Network and its Applications on Speech and Natural Language Processing, Part 3.
발표자: Hung-yi Lee(국립 타이완대 교수)
발표일: 18.7.
Generative adversarial network (GAN) is a new idea for training models, in which a generator and a discriminator compete against each other to improve the generation quality. Recently, GAN has shown amazing results in image generation, and a large amount and a wide variety of new ideas, techniques, and applications have been developed based on it. Although there are only few successful cases, GAN has great potential to be applied to text and speech generations to overcome limitations in the conventional methods.
In the first part of the talk, I will first give an introduction of GAN and provide a thorough review about this technology. In the second part, I will focus on the applications of GAN to speech and natural language processing. I will demonstrate the applications of GAN on voice I will also talk about the research directions towards unsupervised speech recognition by GAN.conversion, unsupervised abstractive summarization and sentiment controllable chat-bot.
Knowledge Graphs have proven to be extremely valuable to rec-
ommender systems, as they enable hybrid graph-based recommen-
dation models encompassing both collaborative and content infor-
mation. Leveraging this wealth of heterogeneous information for
top-N item recommendation is a challenging task, as it requires the
ability of effectively encoding a diversity of semantic relations and
connectivity patterns. In this work, we propose entity2rec, a novel
approach to learning user-item relatedness from knowledge graphs
for top-N item recommendation. We start from a knowledge graph
modeling user-item and item-item relations and we learn property-
specific vector representations of users and items applying neural
language models on the network. These representations are used
to create property-specific user-item relatedness features, which
are in turn fed into learning to rank algorithms to learn a global
relatedness model that optimizes top-N item recommendations. We
evaluate the proposed approach in terms of ranking quality on
the MovieLens 1M dataset, outperforming a number of state-of-
the-art recommender systems, and we assess the importance of
property-specific relatedness scores on the overall ranking quality.
Mathematical Background for Artificial Intelligenceananth
Mathematical background is essential for understanding and developing AI and Machine Learning applications. In this presentation we give a brief tutorial that encompasses basic probability theory, distributions, mixture models, anomaly detection, graphical representations such as Bayesian Networks, etc.
Machine Learning Essentials Demystified part2 | Big Data DemystifiedOmid Vahdaty
achine Learning Essentials Abstract:
Machine Learning (ML) is one of the hottest topics in the IT world today. But what is it really all about?
In this session we will talk about what ML actually is and in which cases it is useful.
We will talk about a few common algorithms for creating ML models and demonstrate their use with Python. We will also take a peek at Deep Learning (DL) and Artificial Neural Networks and explain how they work (without too much math) and demonstrate DL model with Python.
The target audience are developers, data engineers and DBAs that do not have prior experience with ML and want to know how it actually works.
Xây dựng mạng lưới tài năng trẻ trong sáng tạo – khởi nghiệpTri Dung, Tran
Trao đổi về đổi mới sáng tạo (ĐSMT)
Trao đổi về tinh thần khởi nghiệp
Hệ sinh thái ĐMST-Khởi nghiệp và các dịch vụ hỗ trợ
Cố vấn bảo trợ (mentorship)
Ươm tạo và tăng tốc kinh doanh
Đầu tư “hạt giống”
Generative Adversarial Networks : Basic architecture and variantsananth
In this presentation we review the fundamentals behind GANs and look at different variants. We quickly review the theory such as the cost functions, training procedure, challenges and go on to look at variants such as CycleGAN, SAGAN etc.
Session-aware Linear Item-Item Models for Session-based Recommendation (WWW 2...민진 최
This is the official slide for the WWW 2021 paper: Session-aware Linear Item-Item Models for Session-based Recommendation
If you have any questions, please contact zxcvxd@skku.edu.
[GAN by Hung-yi Lee]Part 2: The application of GAN to speech and text processingNAVER Engineering
Generative Adversarial Network and its Applications on Speech and Natural Language Processing, Part 2.
발표자: Hung-yi Lee(국립 타이완대 교수)
발표일: 18.7.
Generative adversarial network (GAN) is a new idea for training models, in which a generator and a discriminator compete against each other to improve the generation quality. Recently, GAN has shown amazing results in image generation, and a large amount and a wide variety of new ideas, techniques, and applications have been developed based on it. Although there are only few successful cases, GAN has great potential to be applied to text and speech generations to overcome limitations in the conventional methods.
In the first part of the talk, I will first give an introduction of GAN and provide a thorough review about this technology. In the second part, I will focus on the applications of GAN to speech and natural language processing. I will demonstrate the applications of GAN on voice I will also talk about the research directions towards unsupervised speech recognition by GAN.conversion, unsupervised abstractive summarization and sentiment controllable chat-bot.
Ranking and Diversity in Recommendations - RecSys Stammtisch at SoundCloud, B...Alexandros Karatzoglou
Slides from my talk at the RecSys Stammtisch at SoundCloud in Berlin. The presentation is split in two part one focusing on ranking and relevance and one on diversity and how to achieve it using genres. We introduce a novel diversity metric called Binomial Diversity.
Tutorial on Deep Learning in Recommender System, Lars summer school 2019Anoop Deoras
I had a fun time giving tutorial on the topic of deep learning in recommender systems at Latin America School on Recommender Systems (LARS) in Fortaleza, Brazil.
Deep Learning with Python: Getting started and getting from ideas to insights in minutes.
PyData Seattle 2015
Alex Korbonits (@korbonits)
This presentation was given July 25, 2015 at the PyData Seattle conference hosted by PyData and NumFocus.
Machine Learning Essentials Demystified part1 | Big Data DemystifiedOmid Vahdaty
Machine Learning Essentials Abstract:
Machine Learning (ML) is one of the hottest topics in the IT world today. But what is it really all about?
In this session we will talk about what ML actually is and in which cases it is useful.
We will talk about a few common algorithms for creating ML models and demonstrate their use with Python. We will also take a peek at Deep Learning (DL) and Artificial Neural Networks and explain how they work (without too much math) and demonstrate DL model with Python.
The target audience are developers, data engineers and DBAs that do not have prior experience with ML and want to know how it actually works.
An overview of gradient descent optimization algorithms Hakky St
勾配降下法についての論文をスライドにしたものです。
This is the slide for study meeting of gradient descent.
I use this paper and this is very good information about gradient descent.
https://arxiv.org/abs/1609.04747
Deep learning: the future of recommendationsBalázs Hidasi
An informative talk about deep learning and its potential uses in recommender systems. Presented at the Budapest Startup Safary, 21 April, 2016.
The breakthroughs of the last decade in neural network research and the quick increasing of computational power resulted in the revival of deep neural networks and the field focusing on their training: deep learning. Deep learning methods have succeeded in complex tasks where other machine learning methods have failed, such as computer vision and natural language processing. Recently deep learning has began to gain ground in recommender systems as well. This talk introduces deep learning and its applications, with emphasis on how deep learning methods can solve long standing recommendation problems.
[GAN by Hung-yi Lee]Part 3: The recent research of my groupNAVER Engineering
Generative Adversarial Network and its Applications on Speech and Natural Language Processing, Part 3.
발표자: Hung-yi Lee(국립 타이완대 교수)
발표일: 18.7.
Generative adversarial network (GAN) is a new idea for training models, in which a generator and a discriminator compete against each other to improve the generation quality. Recently, GAN has shown amazing results in image generation, and a large amount and a wide variety of new ideas, techniques, and applications have been developed based on it. Although there are only few successful cases, GAN has great potential to be applied to text and speech generations to overcome limitations in the conventional methods.
In the first part of the talk, I will first give an introduction of GAN and provide a thorough review about this technology. In the second part, I will focus on the applications of GAN to speech and natural language processing. I will demonstrate the applications of GAN on voice I will also talk about the research directions towards unsupervised speech recognition by GAN.conversion, unsupervised abstractive summarization and sentiment controllable chat-bot.
Knowledge Graphs have proven to be extremely valuable to rec-
ommender systems, as they enable hybrid graph-based recommen-
dation models encompassing both collaborative and content infor-
mation. Leveraging this wealth of heterogeneous information for
top-N item recommendation is a challenging task, as it requires the
ability of effectively encoding a diversity of semantic relations and
connectivity patterns. In this work, we propose entity2rec, a novel
approach to learning user-item relatedness from knowledge graphs
for top-N item recommendation. We start from a knowledge graph
modeling user-item and item-item relations and we learn property-
specific vector representations of users and items applying neural
language models on the network. These representations are used
to create property-specific user-item relatedness features, which
are in turn fed into learning to rank algorithms to learn a global
relatedness model that optimizes top-N item recommendations. We
evaluate the proposed approach in terms of ranking quality on
the MovieLens 1M dataset, outperforming a number of state-of-
the-art recommender systems, and we assess the importance of
property-specific relatedness scores on the overall ranking quality.
Mathematical Background for Artificial Intelligenceananth
Mathematical background is essential for understanding and developing AI and Machine Learning applications. In this presentation we give a brief tutorial that encompasses basic probability theory, distributions, mixture models, anomaly detection, graphical representations such as Bayesian Networks, etc.
Machine Learning Essentials Demystified part2 | Big Data DemystifiedOmid Vahdaty
achine Learning Essentials Abstract:
Machine Learning (ML) is one of the hottest topics in the IT world today. But what is it really all about?
In this session we will talk about what ML actually is and in which cases it is useful.
We will talk about a few common algorithms for creating ML models and demonstrate their use with Python. We will also take a peek at Deep Learning (DL) and Artificial Neural Networks and explain how they work (without too much math) and demonstrate DL model with Python.
The target audience are developers, data engineers and DBAs that do not have prior experience with ML and want to know how it actually works.
Xây dựng mạng lưới tài năng trẻ trong sáng tạo – khởi nghiệpTri Dung, Tran
Trao đổi về đổi mới sáng tạo (ĐSMT)
Trao đổi về tinh thần khởi nghiệp
Hệ sinh thái ĐMST-Khởi nghiệp và các dịch vụ hỗ trợ
Cố vấn bảo trợ (mentorship)
Ươm tạo và tăng tốc kinh doanh
Đầu tư “hạt giống”
Lecture at Hanoi Innovation Week:
Innovation and Entrepreneur are important and nested
How to develop entrepreneurial spirit ?
How to make innovation happens ?
How to start a business?
Where to go for support?
Challenges Encountered by Scaling Up Recommendation Services at Gravity R&DDomonkos Tikk
This talk was given by Bottyan Németh (Gravity R&D Product Owner & Co-founder) in the industry session at ACM Recsys Conference 2015 in Vienna.
Presentation describes the challenges and solution we encountered by scaling up the recommendation services provided by Gravity.
Netflix Recommendations Using Spark + Cassandra (Prasanna Padmanabhan & Roopa...DataStax
Learning is an analytic process of exploring the past in order to predict the future. Hence, being able to travel back in time to create features is critical for machine learning projects to be successful. To enable this, we built a time machine that computes features for any arbitrary time in the recent past for offline experimentation. We also built a real-time stream processing system to capture the interests of members during different times of the day and to quickly adapt to changes in the collective interests of members as it happens in case of real-world events.
Building the time machine for offline experimentation and the real-time infrastructure for online recommendations with Apache Spark (Streaming) and Apache Cassandra empowered us to both scale up the data size by an order of magnitude and train and validate the models in less time. We will delve into the architecture, use case details, data models used for cassandra and share our learnings.
About the Speakers
Prasanna Padmanabhan Engineering Manager, Netflix
Prasanna leads the Data Systems for Personalization team at Netflix. His primary focus is on building various big data infrastructure components that help their algorithmic engineers to innovate faster and improve personalization for Netflix members. In the past, he has built distributed data systems that leverages both batch and stream processing.
Roopa Tangirala Engineering Manager, Netflix
Roopa Tangirala is an experienced engineering leader with extensive background in databases, be they distributed or relational. She manages the database engineering team at Netflix responsible for operating cloud persistent and semipersistent runtime stores for Netflix, which includes Cassandra, Elasticsearch, Dynomite and MySQL databases, by ensuring data availability, durability, and scalability to meet the growing business needs.
Feature Hashing for Scalable Machine Learning: Spark Summit East talk by Nick...Spark Summit
Feature hashing is a powerful technique for handling high-dimensional features in machine learning. It is fast, simple, memory-efficient, and well suited to online learning scenarios. While an approximation, it has surprisingly low accuracy tradeoffs in many machine learning problems.
Feature hashing has been made somewhat popular by libraries such as Vowpal Wabbit and scikit-learn. In Spark MLlib, it is mostly used for text features, however its use cases extend more broadly. Many Spark users are not familiar with the ways in which feature hashing might be applied to their problems.
In this talk, I will cover the basics of feature hashing, and how to use it for all feature types in machine learning. I will also introduce a more flexible and powerful feature hashing transformer for use within Spark ML pipelines. Finally, I will explore the performance and scalability tradeoffs of feature hashing on various datasets.
Netflix's Recommendation ML Pipeline Using Apache Spark: Spark Summit East ta...Spark Summit
Netflix is the world’s largest streaming service, with 80 million members in over 250 countries. Netflix uses machine learning to inform nearly every aspect of the product, from the recommendations you get, to the boxart you see, to the decisions made about which TV shows and movies are created.
Given this scale, we utilized Apache Spark to be the engine of our recommendation pipeline. Apache Spark enables Netflix to use a single, unified framework/API – for ETL, feature generation, model training, and validation. With pipeline framework in Spark ML, each step within the Netflix recommendation pipeline (e.g. label generation, feature encoding, model training, model evaluation) is encapsulated as Transformers, Estimators and Evaluators – enabling modularity, composability and testability. Thus, Netflix engineers can build our own feature engineering logics as Transformers, learning algorithms as Estimators, and customized metrics as Evaluators, and with these building blocks, we can more easily experiment with new pipelines and rapidly deploy them to production.
In this talk, we will discuss how Apache Spark is used as a distributed framework we build our own algorithms on top of to generate personalized recommendations for each of our 80+ million subscribers, specific techniques we use at Netflix to scale, and the various pitfalls we’ve found along the way.
By popular demand, here is a case study of my first Kaggle competition from about a year ago. Hope you find it useful. Thank you again to my fantastic team.
In this talk we explore how to build Machine Learning Systems that can that can learn "continuously" from their mistakes (feedback loop) and adapt to an evolving data distribution.
The youtube link to video of the talk is here:
https://www.youtube.com/watch?v=VtBvmrmMJaI
Horizon: Deep Reinforcement Learning at ScaleDatabricks
To build a decision-making system, we must provide answers to two sets of questions: (1) ""What will happen if I make decision X?"" and (2) ""How should I pick which decision to make?"".
Typically, the first set of questions are answered with supervised learning: we build models to forecast whether someone will click on an ad, or visit a post. The second set of questions are more open-ended. In this talk, we will dive into how we can answer ""how"" questions, starting with heuristics and search. This will lead us to bandits, reinforcement learning, and Horizon: an open-source platform for training and deploying reinforcement learning models at massive scale. At Facebook, we are using Horizon, built using PyTorch 1.0 and Apache Spark, in a variety of AI-related and control tasks, spanning recommender systems, marketing & promotion distribution, and bandwidth optimization.
The talk will cover the key components of Horizon and the lessons we learned along the way that influenced the development of the platform.
Author: Jason Gauci
Predictive Model and Record Description with Segmented Sensitivity Analysis (...Greg Makowski
Describing a predictive data mining model can provide a competitive advantage for solving business problems with a model. The SSA approach can also provide reasons for the forecast for each record. This can help drive investigations into fields and interactions during a data mining project, as well as identifying "data drift" between the original training data, and the current scoring data. I am working on open source version of SSA, first in R.
Machine Learning Foundations for Professional ManagersAlbert Y. C. Chen
20180804@Taiwan AI Academy, Hsinchu
6 hour lecture for those new to machine learning, to grasps the concepts, advantages and limitations of various classical machine learning methods. More importantly, to learn the skills to break down large complicated AI projects into manageable pieces, where features and functionalities could be added incrementally and annotated data accumulated. Take home message: machine learning is always a delicate balance between model complexity M and number of data N so that the trained classifier generalizes well and does not overfit.
DutchMLSchool. ML: A Technical PerspectiveBigML, Inc
DutchMLSchool. Machine Learning: A Technical Perspective
TITLE AS IN SCHEDULE - Main Conference: Introduction to Machine Learning.
DutchMLSchool: 1st edition of the Machine Learning Summer School in The Netherlands.
The Machine Learning Workflow with AzureIvo Andreev
Machine learning is not black magic but a discipline that involves data analysis, data science and of course – hard work. From searching patterns in data, applying algorithms to converting to usable predictions, you would need background and appropriate tools. In this session, we will go through major approaches to prepare data, build and deploy ML models in Azure (ML Studio, DataScience VM, Jupyter Notebook). Most importantly – based on some examples from the real world, we will provide you with a workflow of best practices.
Model-Based User Interface Optimization: Part IV: ADVANCED TOPICS - At SICSA ...Aalto University
Tutorial on Model-Based User Interface Optimization. Part IV: ADVANCED TOPICS.
Presented by Antti Oulasvirta (Aalto University) at SICSA Summer School on Computational Interaction in 2015 in Glasgow. Note: This one-day lecture is divided into multiple parts.
The Power of Auto ML and How Does it WorkIvo Andreev
Automated ML is an approach to minimize the need of data science effort by enabling domain experts to build ML models without having deep knowledge of algorithms, mathematics or programming skills. The mechanism works by allowing end-users to simply provide data and the system automatically does the rest by determining approach to perform particular ML task. At first this may sound discouraging to those aiming to the “sexiest job of the 21st century” - the data scientists. However, Auto ML should be considered as democratization of ML, rather that automatic data science.
In this session we will talk about how Auto ML works, how is it implemented by Microsoft and how it could improve the productivity of even professional data scientists.
Efficiency gains in inversion based interpretation through computerDustin Dewett
This presentation describes a workflow for using self-organizing maps to aid in the interpretation of seismic inversion products. The described method will allow an individual with little training in rock physics or quantitative interpretation (QI) to identify anomalies within the data quickly and easily.
Towards agile formal methods
The main goal of this work is to overcome the aforementioned limitations by enabling automated decision gates in performance testing of microservices that allow requirements traceability. We seek to achieve this goal by endowing common agile practices used in microservice performance testing, with the ability to automatically learn and then formally verify a performance model of the System Under Test (SUT) to achieve strong assurances of quality. Even if the separation between agile and formal methods increased over the years, we support the claim that formal methods are at a stage where they can be effectively incorporated into agile methods to give them rigorous engineering foundations and make them systematic and effective with strong guarantees.
Continuous Learning Systems: Building ML systems that learn from their mistakesAnuj Gupta
Won't it be great to have ML models that can update their “learning” as and when they make mistake and correction is provided in real time? In this talk we look at a concrete business use case which warrants such a system. We will take a deep dive to understand the use case and how we went about building a continuously learning system for text classification. The approaches we took, the results we got.
Recommenders on video sharing portals - business and algorithmic aspectsDomonkos Tikk
This talk was given at HTE Medianet 2015 conference on the business ecosystem and its impact and requirement on recommender solutions on user generated content (UGC) video sharing portals (like Youtube, Dailymotion, etc). Besides the intro on Gravity R&D and the business model, we present some information on a real-world case study. We show that larger view counts are directly influence the recommendation quality.
This is the slides from conTEXT conference held by SPSS Consulting (Hungary) at 2014.11.21. Slides are in Hungarian
Tartalomgazdagítás szövegbányászattal Linked Open Data alapján és felhasználása ajánlórendszerekben
Ajánlórendszerek jellemzően két adatforrás alapján dolgoznak: a felhasználók tartalomfogyasztási szokásaik (collaborative filtering) és a tartalomak metaadatai alapján (content based filtering). A tartalomleíró adatoknak nagy előnye, hogy az ajánlások könnyen magyarázhatóak a felhasználóknak (azért ajánjuk, mert szereted Brad Pitt filmjeit, stb.), és már új tartalmak esetén is alkalmazhatók. Ezért nyilván nagyon fontos, hogy jó minőségűek és minél gazdagabbak legyenek a tartalmakat leíró metaadatok. Ezek a feltételek azonban gyakran nem teljesülnek, ezért szükség ún. tartalomgazdagításra (content enrichment), hogy jobban jellemezhetőek legyenek a tartalmak. A Gravity alkalmazott megoldás nyilvánosan elérhető adatbázisok (Linked Open Data, LOD) segítségével végzi el a tartalomgazdagítást, mint pl. a Freebase és a DBpedia. A probléma számos szövegbányászati részfeladatot tartalmaz, mint pl. névelemek felismerése és egyértelműsítése (színész, rendező neve; film címe), névelemek tulajdonságainak meghatározása (pl. színész fontosabb adatai) különböző forrásokból származó adatok egyesítése, átfedő, ill. esetleg inkonzisztens adatok kanonizálása. Az előadás során röviden ismertetésre kerül az általunk alkalmazott RDF alapú megoldás, a SPARQL lekérdezőnyelv és alkalmazása, és rámutatunk néhány lehetséges megoldására a szövegbányázati feladatoknak.
Idomaar is an open-source benchmarking framework for recommender systems created by the CrowdRec EU-project. It enables impartial evaluation of recommenders solutions from different aspect: (1) recommendation quality (2) technical aspects (3) business aspects.
Main contributors of Idomaar: Moviri, Gravity RD, Technical University of Delft, Technical University Berlin
The slideshow was presented at ICMA Conference in Helsinki at the "How to Turn Big Data into Dollars" Workshop organized by Gravity R&D,
The presentation reviews the heterogeneity of data sources at classified media, shows the massive size of data available, and give some insights how to use those data for personalization in various scenarios.
Context-aware similarities within the factorization framework - presented at ...Domonkos Tikk
Talk deals with a practical recommendation sceaario - item-2-item recommendation (similar/related items) with implicit feedback and context. Solution is provided in the factorization framework.
Paper abstract (to appear in ACM digital Library) Item-to-item recommendation - when the most similar items sought to the actual item - is an important recommendation scenario in practical recommender systems. One way to solve this task is to use the similarity between item feature vectors of factorization models. By doing so, one may transfer the well-known accuracy of factorization models observed at the personalized recommendations to the item-to-item case. This paper introduces context-awareness to item similarities in the factorization framework. Two levels of context-aware similarities are defined and applied to two context-aware implicit feedback based factorization methods (iTALS and iTALSx). We investigate the advantages and drawbacks of the approaches on four real life implicit feedback data sets and we characterize the conditions for their application. The results suggest that it is worth using contextual information for item-to-item recommendations in the factorization framework, however, one should carefully select the appropriate method to achieve similar accuracy gain than in the case of the more general item-to-user recommendation scenario.
Slides from CARR 2012 WS - Enhancing Matrix Factorization Through Initializat...Domonkos Tikk
Executive summary: The paper propose a new method to solve the cold start problem for matrix factorization using metadata. The method works with the realistic implicit feedback scenario. With a smart initialization of the feature matrices better performance values were achieved on several data sets.
Paper abstract: The implicit feedback based recommendation problem—
when only the user history is available but there are no ratings—is a much harder task than the explicit feedback based recommendation problem, due to the inherent uncertainty of the interpretation of such user feedbacks. Still, this practically important recommendation task received less attention and therefore there are only a few common implicit feedback based algorithms and benchmark datasets. This paper focuses on a common matrix factorization method for the implicit problem and investigates if recommendation performance can be improved by appropriate initialization of the feature vectors before training. We present a general initialization framework that preserves the similarity between entities (users/items) when creating the initial feature vectors,
where similarity is defined using e.g. context or metadata information. We demonstrate how the proposed initialization framework can be coupled with MF algorithms. The efficiency of the initialization is evaluated using various context and metadata based similarity concepts on two implicit variants of the MovieLens 10M
dataset and one real life implicit database. It is shown that performance gain can attain 10% improvement in recall@50 and in AUC@50.
Fast ALS-Based Tensor Factorization for Context-Aware Recommendation from Imp...Domonkos Tikk
Executive summary: The paper deals with the implicit feedback problem for recommender systems, and propose a fast context-aware tensor factorization method that can integrate any kind of contextual information.
Paper abstract: Albeit the implicit feedback based recommendation problem—when only the user history is available but there are no ratings—is the most typical setting in real-world applications, it is much less researched than the explicit feedback case. State-of-the-art algorithms that are efficient on the explicit case cannot be straightforwardly transformed to the implicit case if scalability should be maintained. There are few implicit feedback benchmark datasets, therefore new ideas
are usually experimented on explicit benchmarks. In this paper, we pro-
pose a generic context-aware implicit feedback recommender algorithm,
coined iTALS. iTALSapplies a fast, ALS-basedtensor factorization learn-
ing method that scales linearly with the number of non-zero elements
in the tensor. The method also allows us to incorporate various contex-
tual information into the model while maintaining its computational effi-
ciency. We present two context-aware implementation variants of iTALS.
The first incorporates seasonality and enables to distinguish user behav-
ior in different time intervals. The other views the user history as sequen-
tial information and has the ability to recognize usage pattern typical
to certain group of items, e.g. to automatically tell apart product types
that are typically purchased repetitively or once. Experiments performed
on five implicit datasets (LastFM 1K, Grocery, VoD, and “implicitized”
Netflix and MovieLens 10M) show that by integrating context-aware
information with our factorization framework into the state-of-the-art
implicit recommender algorithm the recommendation quality improves
significantly.
Recommender Systems Evaluation: A 3D Benchmark - presented at RUE 2012 worksh...Domonkos Tikk
Recommender systems add value to vast content resources by matching users with items of interest. In recent years, immense progress has been made in recommendation techniques. The evaluation of these has however not been matched and is threatening to impede the further development of recommender systems. In this paper we propose an approach that addresses this impasse by formulating a novel evaluation concept adopting aspects from recommender systems research and industry. Our model can express the quality of a recommender algorithm from three perspectives, the end consumer (user), the service provider and the vendor (business and technique for both). We review current benchmarking activities and point out their shortcomings, which are addressed by our model. We also explain how our 3D benchmarking framework would apply to a specific use case.
1.Wireless Communication System_Wireless communication is a broad term that i...JeyaPerumal1
Wireless communication involves the transmission of information over a distance without the help of wires, cables or any other forms of electrical conductors.
Wireless communication is a broad term that incorporates all procedures and forms of connecting and communicating between two or more devices using a wireless signal through wireless communication technologies and devices.
Features of Wireless Communication
The evolution of wireless technology has brought many advancements with its effective features.
The transmitted distance can be anywhere between a few meters (for example, a television's remote control) and thousands of kilometers (for example, radio communication).
Wireless communication can be used for cellular telephony, wireless access to the internet, wireless home networking, and so on.
This 7-second Brain Wave Ritual Attracts Money To You.!nirahealhty
Discover the power of a simple 7-second brain wave ritual that can attract wealth and abundance into your life. By tapping into specific brain frequencies, this technique helps you manifest financial success effortlessly. Ready to transform your financial future? Try this powerful ritual and start attracting money today!
Multi-cluster Kubernetes Networking- Patterns, Projects and GuidelinesSanjeev Rampal
Talk presented at Kubernetes Community Day, New York, May 2024.
Technical summary of Multi-Cluster Kubernetes Networking architectures with focus on 4 key topics.
1) Key patterns for Multi-cluster architectures
2) Architectural comparison of several OSS/ CNCF projects to address these patterns
3) Evolution trends for the APIs of these projects
4) Some design recommendations & guidelines for adopting/ deploying these solutions.
ER(Entity Relationship) Diagram for online shopping - TAEHimani415946
https://bit.ly/3KACoyV
The ER diagram for the project is the foundation for the building of the database of the project. The properties, datatypes, and attributes are defined by the ER diagram.
ER(Entity Relationship) Diagram for online shopping - TAE
Lessons learnt at building recommendation services at industry scale
1. Lessons learnt at building
recommendation services
at industry scale
Domonkos Tikk
Gravity R&D
Industry keynote @ ECIR 2016
@domonkostikk
2. Credits to colleagues
3/24/2016
Bottyán Németh
Product Owner and co-founder
István Pilászy
Head of Development and co-founder
Balázs Hidasi
Head of Data Mining & Research
Gábor Vincze
Head of Global Service
György Dózsa
Head of Web Integrations
and many others…
4. Who we are and what we do
4
Gravity R&D is a recommender system vendor company
We provide recommendation as a service since 2009 for
our customers all around the globe
11. Short summary of Netflix Prize
3/24/2016
• 2006–2009
• Predict movie ratings (explicit feedback)
• Content based filtering (CBF) did not work
• Classical CF methods (item-kNN, user-kNN) did not
work
• Matrix factorization was extremely effective
• We were fully in love with matrix factorization
12. Schematic of matrix factorization
3/24/2016
• Model
How we approximate user preferences
𝑟𝑢,𝑖 = 𝑝 𝑢
𝑇 𝑞𝑖
• Objective function (error function)
What we want to minimize or optimize?
E.g. optimize for RMSE with regularization L = (𝑢,𝑖)∈𝑇𝑟𝑎𝑖𝑛 𝑟𝑢,𝑖 −
Learning
≈ 𝑆𝐼
𝑆𝐼
𝑆 𝑈 𝑆 𝑈
𝐾
𝐾
17. Netflix Prize demo / 1
3/24/2016
• In 2009 we created a public demo mainly for investors
• Users can rate movies and get recommendations
• What do you expect from a demo?
Be relevant even after 1 rating
Users will provide their favorite movies first
Be relevant after 2 ratings: both movies should affect the
results
18. Netflix Prize demo / 2
3/24/2016
• Using a good MF model with K=200 factors and biases
• Use linear regression to compute user feature vector
• Recs after rating a romantic movie Notting Hill, 1999
OK Score Title
4.6916 The_Shawshank_Redemption/1994
4.6858 House,_M.D.:_Season_1/2004
4.6825 Lost:_Season_1/2004
4.5903 Anne_of_Green_Gables:_The_Sequel/1987
4.5497 Lord_of_the_Rings:_The_Return_of_the_King/2003
19. Netflix Prize demo / 3
3/24/2016
• Idea: turn off item bias during recommendation.
• Result are fully relevant
• Even with 10 factors, it is very good
OK Score Title
4.3323 Love_Actually/2003
4.3015 Runaway_Bride/1999
4.2811 My_Best_Friend's_Wedding/1997
4.2790 You've_Got_Mail/1998
4.1564 About_a_Boy/2002
20. Netflix Prize demo / 4
3/24/2016
• Now give 5-star rating to Saving Private Ryan / 1998
• Almost no change in the list
OK Score Title
4.5911 You've_Got_Mail/1998
4.5085 Love_Actually/2003
4.3944 Sleepless_in_Seattle/1993
4.3625 Runaway_Bride/1999
4.3274 My_Best_Friend's_Wedding/1997
21. Netflix Prize demo / 5
3/24/2016
• Idea: set item biases to zero before computing user feature vector
• 5th rec is romantic + war
• Conclusion: MF is good, but rating and ranking are very different
OK Score Title
4.5094 You've_Got_Mail/1998
4.3445 Black_Hawk_Down/2001
4.3298 Sleepless_in_Seattle/1993
4.3114 Love_Actually/2003
! 4.2805 Apollo_13/1995
24. Business model: Trabant vs. Rolls Royce
• Cheap for client
• Simple functionality
• Low performance
• No customization
• Limited warranty
• Works if sold in large
quantities
• Expensive for client
• Complex functionality
• High performance
• Fully customization
• Full warranty (SLA)
• Few sales can bring
enough return
25. Our decision in 2009 was: Rolls Royce
• Expensive for client
• Complex functionality
• High performance
• Fully customization
• Full warranty (SLA)
• Few sales can bring
enough return
26. # of requests
26
Vatera.hu largest online marketplace in Hungary
served by one “server”
Alexa TOP100 video chat webpage
(~40M recommendation requests / day):
Served by 5 application servers and 1 DB
Too many events to store in MySQL using
Cassandra (v0.6)
Training time for IALS too long speedup by IALS1
Max. 5 sec latency in “product” availability
28. Reaching the limits
28
Even if the technology is widely used if you reach its
limits the optimization is very costly / time consuming.
Java GC – service collapsed because increased minor GC
times due to a JVM bug (26th of January 2013)
Maintaining MySQL with lots of data (optimize table,
slave replication lag, faster storage device)
31. # of items
31
How to store item model / metadata in memory to serve
requests fast?
VS.
Auto increment IDs for the items?
231 (~2 billions) is not enough
35. Industry vs. academia
3/24/2016
• In Academic papers
50% explicit feedback
50% implicit feedback
o 49.9% personal
o 0.1% item2item
• At gravityrd.com:
1% explicit feedback
99% implicit feedback
o 15% personal
o 84% item2item
• Sites where rating is crucial tend to create their own rec engine
• Even if there is explicit rating, there are more implicit feedback
36. Implicit vs. explicit ratings
• Standard SGD based
learning does not work
(complexity issues)
• Implicit ALS
• Approximate versions of
IALS
with coordinate descent*
with conjugate gradient**
* I Pilászy, D Zibriczky, D Tikk, Fast ALS-based matrix factorization for explicit and implicit feedback datasets,
RecSys 2010,
** G Takács, I Pilászy, D Tikk, Applications of the conjugate gradient method for implicit feedback, collaborative
filtering, RecSys 2011,
37. What is the problem with the explicit
objective function
3/24/2016
• L = (𝑢,𝑖)∈𝑇 𝑟𝑢,𝑖 − 𝑟𝑢,𝑖
2
+ 𝜆 𝑈 𝑢=1
𝑆 𝑈
𝑃𝑢
2
+𝜆𝐼 𝑖=1
𝑆 𝐼
𝑄𝑖
2
• The matrix to be factorized contains 0s and 1s
If we consider only the positive events (1s)
o Predicting 1s everywhere, minimizes 𝐿 trivially
o Some minor differences may occur due to regularization
• Modified objective function (including zeros)
L = 𝑢=1,𝑖=1
𝑆 𝑈,𝑆 𝐼
𝑟𝑢,𝑖 − 𝑟𝑢,𝑖
2
+ 𝜆 𝑈 𝑢=1
𝑆 𝑈
𝑃𝑢
2
+𝜆𝐼 𝑖=1
𝑆 𝐼
𝑄𝑖
2
Number of terms increased
#zeros ≫ #ones
o All zero prediction gives pretty good 𝐿
38. Why „explicit” optimization suffers
3/24/2016
• Complexity of the best explicit method
𝑂 𝑇 𝐾
Linear in the number of observed ratings
• Implicit feedback
One should consider negative implicit feedback („missing rating”)
There is no real missing rating in the matrix
o An element is either 0 or 1, no empty cells
Complexity: 𝑂 𝑆 𝑈 𝑆𝐼 𝐾
Sparse data (< 1%, in general)
𝑆 𝑈 𝑆𝐼 ≫ 𝑇
39. iALS – objective function
3/24/2016
• 𝐿 = 𝑢=1,𝑖=1
𝑆 𝑈,𝑆 𝐼
𝑤 𝑢,𝑖 𝑟𝑢,𝑖 − 𝑟𝑢,𝑖
2
+ 𝜆 𝑈 𝑢=1
𝑆 𝑈
𝑃𝑢
2
+ 𝜆𝐼 𝑖=1
𝑆 𝐼
𝑄𝑖
2
• Weighted MSE
• 𝑤 𝑢,𝑖 =
𝑤 𝑢,𝑖 if (𝑢, 𝑖) ∈ 𝑇
𝑤0 otherwise
𝑤0 ≪ 𝑤 𝑢,𝑖
• Typical weights: 𝑤0 = 1, 𝑤 𝑢,𝑖 = 100 ∗ 𝑠𝑢𝑝𝑝 𝑢, 𝑖
• Create two matrices from the events
(1) Preference matrix
o Binary
o 1 represents the presence of an event
(2) Confidence matrix
o Interprets our certainty on the corresponding values in the first matrix
o Negative feedback is much less certain
40. Complexity of iALS
3/24/2016
• Total cost: 𝑂 𝐾3 𝑆 𝑈 + 𝑆𝐼 + 𝐾2 𝑁+
Linear in the number of events
Cubic in the number of features
• In practice: 𝑆 𝑈 + 𝑆𝐼 ≪ 𝑁+
so for small 𝐾 the second term
dominates
Quadratic in the number of features
• Approximate versions are even faster
CG scales linearly in number of features for small 𝐾
41. Training time using speed-ups
3/24/2016
• ~1000 users
• ~170k items
• ~19M events
0.00
100.00
200.00
300.00
400.00
500.00
600.00
700.00
800.00
5
10
15
20
25
30
35
40
45
50
55
60
65
70
75
80
85
90
95
100
Runningtime(s)
Number of features (K)
ALS
CG
CD
43. Task 2: item-2-item recommendations
3/24/2016
• What is item-to-item recommendation?
People who viewed this also viewed: …
Viewed, watched, purchased, liked, favored, etc.
• Ignoring the current user
• The recommendation should be relevant to the current
item
• Very common scenario
45. Data volume and time
3/24/2016
• Data characteristics (after data
retention):
Number of active users: 100k – 100M
Number of active items : 1k – 100M
Number of relations between them:
10M – 10B
• Response time: must be within
200ms
• We cannot give 199ms for MF
prediction + 1ms business logic
46. Time complexity of MF for implicit feedback
3/24/2016
• During training
𝑁+
= #events, S 𝑈 = #users, 𝑆𝐼 = #items
implicit ALS: 𝑂 𝐾3
𝑆 𝑈 + 𝑆𝐼 + 𝐾2
𝑁+
o with Coordinate Descent: 𝑂 𝐾2
𝑆 𝑈 + 𝑆𝐼 + 𝐾𝑁+
o with CG: the same, but more stable.
BPR: 𝑂 𝐾𝑁+
CliMF:𝑂 𝐾𝑁+
⋅ avg(user support)
• During recommendation: 𝐼 ⋅ 𝐾
• Not practical if 𝐼 > 100k, 𝐾 > 100
• You have to increase 𝐾 as 𝐼 grows
47. i2i recommendations with SVD / 2
3/24/2016
• Recommendations should seem relevant
• You can expect that movies of the same trilogy are similar to each
other
• We defined the following metric:
For movies A and B of a trilogy, check if B is amongst the top-5 most
similar items of A.
Score: 0 or 1
A trilogy can provide 6 such pairs (12 for tetralogies)
Sum up this for all trilogies
• We used a custom movie dataset
• Good metric for CF item-to-item, bad metric for CBF item-to-item
48. i2i recommendations with SVD / 3
3/24/2016
• Evaluating for SVD with different number of factors
• Using cosine similarity between SVD feature vectors
• more factors provide better results
• Why not use the original space?
• Who wants to run SVD with 500 factors?
• Score of neighbor method (using cosine similarity between
original vectors): 169
𝐾 10 20 50 100 200 500 1000 1500
score 72 82 95 96 106 126 152 158
49. I2i recommendations with SVD / 4
3/24/2016
• What does a 200-factor SVD recommend to Kill Bill: Vol. 1
• Really bad recommendation
OK Cos
Sim
Title
0.299 Kill Bill: Vol. 2
0.273 Matthias, Matthias
0.223 The New Rijksmuseum
0.199 Naked
0.190 Grave Danger
50. i2i recommendations with SVD / 5
3/24/2016
• What does a 1500-factor SVD recommend to Kill Bill: Vol. 1
• Good, but uses lots of CPU
• But that is an easy domain, with 20k movies!
OK Cos
Sim
Title
0.292 Kill Bill: Vol. 2
! 0.140 Inglourious Basterds
! 0.133 Pulp Fiction
0.131 American Beauty
! 0.125 Reservoir Dogs
51. Implementing an item-to-item method / 1
3/24/2016
We implemented the following article:
Noam Koenigstein and Yehuda Koren. "Towards scalable and
accurate item-oriented recommendations." Proceedings of the 7th
ACM conference on Recommender systems. ACM, 2013.
• They define a new metric for i2i evaluation:
MPR (Mean Percentile Rank):
If user visits A, and then B, then recommend for A, and see the
position of B in that list.
• They propose a new method (EIR, Euclidean Item Recommender) ,
that assigns feature vector for each item, so that if A is close to B,
then users frequently visit B after A.
• They don’t compare it with pure popularity method
52. Implementing an item-to-item method / 2
3/24/2016
Results on a custom movie dataset:
• SVD and other methods can’t beat the new method
• Popularity method is better or on-pair with the new method
• Recommendations for Pulp Fiction:
SVD New method
Reservoir Dogs A Space Odyssey
Inglourious Basterds A Clockwork Orange
Four Rooms The Godfather
The Shawshank Redemption Eternal Sunshine of the Spotless Mind
Fight Club Mulholland Drive
53. Implementing an item-to-item method / 3
3/24/2016
Comparison
method
metadata similarity
(larger is better)
MPR
(smaller is better)
cosine 7.54 0.68
Jaccard 7.59 0.68
Association rules 6.44 0.68
pop 1.65 0.25
random 1.44 0.50
EIR 5.00 0.25
54. Summary of EIR
3/24/2016
• This method is better in MPR than many other methods
• It is on pair with Popularity method
• It is worse in metadata-based similarity
• Sometimes recommendations look like they were
random
• Sensitive to the parameters
• Very few articles are dealing with CF item-to-item recs
60. Case studies on CTR / 3
3/24/2016
Using BPR vs. item-kNN on a video site for personal
recommendations
Measuring number of clicks on recommendations
Result: 4% more clicks for BPR
62. Critiques of MF
3/24/2016
• Lots of parameters to tune
• Needs many iteration over the data
• If there is no inter-connection between two item sets,
they can get similar feature vectors.
• Sensitive to noise in data and cold-start
• Not the best for item-to-item recs, especially when
many neighbors already exist
63. When to use MF
3/24/2016
• One dense domain (e.g. movies), with not too many
items (e.g. less than 100k)
• Feedback is taste-based
• For personalized recommendations (e.g. newsletter)
• Do always A/B testing
• Smart blending (e.g. using it for high supported items)
• Usually better for offline evaluation metrics
66. Technology overview
66
• Performance: Gravity’s performance
oriented architecture enables real-time
response to the always changing
environment and user behavior
• Algorithms: more than 100 different
recommendation algorithm enables true
personalization and to reach the highest
KPIs in different domains
• Infrastructure: fast response times all
around the globe and data security thanks
to the private cloud infrastructure located
in 4 different data centers
• Flexibility: the advanced business rule
engine with intuitive user interface allows
to satisfy various business requirements
Performance
140M requests
served daily
Algorithms
30 man-years
invested
Infrastructure
4 data centers
globally
Flexibility
100s of logics
configurable
72. Deep learning: Session based
recommendations
• User profile separate sessions
User identification problem
Sessions of different purposeses
o Buy for herself / present
o Purchase products that specify a need (e.g. TV now, fridge 2 weeks later)
o Intent / goal of a browsing sessions of the same user can be different
• Usual solution: Item-to-item recommendations
Previous history is not considered
No personalized experience
Extra round for finding the best fit
• Next event prediction:
Given the events in the session (so far) what is the next most likely event?
73. Session based recommendations with RNN
• Item-to-session recommendations
• Using RNNs (GRU, LSTM)
• Network with many features
• Distinctive features
Session-parallel mini-batches
Sampling on the output layer
Ranking loss
o BPR
o TOP1
GRU layer
Feedforward layers
GRU layer
Input: actual item, 1-of-N coding
Embedding layer
GRU layer
…
Output: scores on items
76. Direct usage of content for recommendations
• User’s decision (click or not click)
Title
Image
Description
• Pipeline
Automatic feature extraction from content (text, images, music, video)
Feed features to the RNN recommender
• Other usages
„Truly similar” item recommendation
„X is to Y like A is to B” recommendations
Etc.
• High potential
77. Recoplatform: RaaS for SMBs
3/24/2016
• www.recoplatform.com
• Self service solution
• Automated quick and
easy integration
• Priced to scale with
business size