ML Resources

Resources listed here are on my to-read, to-do, to-try lists, not endorsements. I collect these typically at the beginning of projects and I go through them as time progresses when I want to explore a new way of looking at the problem I am working on.

Ranking & Recommendations

Introductory Resources

1. A Short Introduction to Learning to Rank

Search

1. xQuAD : Exploiting Query Reformulations for Web Search Result Diversification WWW 2010
2. Counterfactual Estimation and Optimization of Click Metrics for Search Engines Microsoft Facebook WWW 2015
3. Cascade Ranking for Operational E-commerce Search Alibaba KDD 2017

Multi-Objective Ranking

1. Click Shaping to Optimize Multiple Objectives Yahoo! KDD 2011
2. Constrained Optimization for Homepage Relevance LinkedIn WWW 2015
3. Multi-objective Relevance Ranking Amazon SIGIR 2019
4. Personalized Click Shaping through Lagrangian Duality for Online Recommendation LinkedIn Facebook SIGIR 2012
5. Whole Page Optimization with Global Constraints, Video Amazon KDD 2019
6. A Pareto-Efficient Algorithm for Multiple Objective Optimization in E-Commerce Recommendation Alibaba Rutgers University Kwai Inc. RecSys 2019
7. Optimizing Multiple Objectives in Collaborative Filtering UCL RecSys 2010
8. Multi-Criteria Service Recommendation Based on User Criteria Preferences University of Manchester RecSys 2011
9. Multiple Objective Optimization in Recommender Systems LinkedIn RecSys 2012
10. Pareto-Efficient Hybridization for Multi-Objective Recommender Systems Universidade Federal de Minas Gerais Zunnit Technologies RecSys 2012
11. TasteWeights: A Visual Interactive Hybrid Recommender System RecSys 2012
12. MPR: Multi-Objective Pairwise Ranking George Mason University SAP Labs RecSys 2017
13. User Preference Learning in Multi-criteria Recommendations using Stacked Auto Encoders NIT Rourkela RecSys 2018
14. Portfolio Selections in P2P Lending: A Multi-Objective Perspective USTC University of Arizona KDD 2016
15. A Multi-Objective Learning to re-Rank Approach to Optimize Online Marketplaces for Multiple Stakeholders Expedia
16. Random Walk based Entity Ranking on Graph for Multidimensional Recommendation Seoul National University RecSys 2011
17. User Effort vs. Accuracy in Rating-based Elicitation RecSys 2012
18. Movie Recommender System for Profit Maximization RecSys 2013

Bias in Ranking

1. On Bias Problem in Relevance Feedback Tsinghua University University of California CIKM 2011
2. Towards an Effective and Unbiased Ranking of Scientific Literature through Mutual Reinforcement CIKM 2012
3. A Retrievability Analysis: Exploring the Relationship Between Retrieval Bias and Retrieval Performance University of Glasgow CIKM 2014
4. Algorithmic Bias: Do Good Systems Make Relevant Documents More Retrievable? University of Glasgow University of Strathclyde CIKM 2017
5. Differentiable Unbiased Online Learning to Rank University of Amsterdam CIKM 2018
6. Estimating Clickthrough Bias in the Cascade Model Spotify CIKM 2018
7. Correcting for Recency Bias in Job Recommendation RMIT University University of Utah GO1 CIKM 2019
8. On Heavy-user Bias in A/B Testing UC Berkeley Microsoft CIKM 2019
9. Managing Popularity Bias in Recommender Systems with Personalized Re-ranking University of Colorado DePaul University FLAIRS 2019
10. A Methodology for Learning, Analyzing, and Mitigating Social Influence Bias in Recommender Systems UC Berkeley RecSys 2014
11. On Over-Specialization and Concentration Bias of Recommendations: Probabilistic Neighborhood Selection in Collaborative Filtering Systems NYU RecSys 2014
12. Controlling Popularity Bias in Learning to Rank Recommendation DePaul University RecSys 2017
13. Modeling the Assimilation-Contrast Effects in Online Product Rating Systems: Debiasing and Recommendations CUHK RecSys 2017
14. Sampling-Bias-Corrected Neural Modeling for Large Corpus Item Recommendations Google RecSys 2019
15. Sample Selection Bias Correction Theory Google
16. Addressing Marketing Bias in Product Recommendations Airbnb UCSD Twitter WSDM 2020

Cross-Sell, Substitutes, Complementary Item Recommendation

1. Representing and Recommending Shopping Baskets with Complementarity, Compatibility, and Loyalty, GitHub Microsoft UCSD CIKM 2018
2. Inferring Networks of Substitutable and Complementary Products, Video, Video Pinterest UCSD Stanford KDD 2015
3. Quality-Aware Neural Complementary Item Recommendation, GitHub, Video Texas A&M University SIGIR 2015
4. Complementary Recommendations at eBay: Tackling the Challenges of a Semi-Unstructured Marketplace, Blog
5. Mining Frequent Patterns without Candidate Generation Simon Fraser University
6. Mining Frequent Itemsets through Progressive Sampling with Rademacher Averages Two Sigma Investments Brown University KDD 2015
7. Mining High Utility Itemsets without Candidate Generation Wuhan University Carleton University CIKM 2012
8. Improving Recommendation Accuracy using Networks of Substitutable and Complementary Products The Chinese University of Hong Kong UCSD IJCNN 2017
9. Modelling Complementary Products and Customer Preferences with Context Knowledge for Online Recommendation Walmart Labs KDD 2019
10. Collaborative Sequence Prediction for Sequential Recommender University of Chinese Academy of Sciences CIKM 2017
11. Domain Knowledge Based Personalized Recommendation Model and Its Application in Cross-selling Chinese Academy of Sciences University of Nebraska at Omaha ICCS 2012
12. Recommending Complementary Products in E-Commerce Push Notifications with a Mixture Model Approach Alibaba SIGIR 2017
13. CRAFT: Complementary Recommendations Using Adversarial Feature Transformer Amazon
14. Knowledge-aware Complementary Product Representation Learning Walmart Labs WSDM 2020
15. c+ GAN: Complementary Fashion Item Recommendation Microsoft KDD 2019
16. Association Rules with Graph Patterns VLDB 2015
17. Cross-sell: A Fast Promotion-Tunable Customer-item Recommendation Method Based on Conditionally Independent Probabilities Vignette Corporation
18. A Fast Algorithm for Mining Utility-Frequent Itemsets
19. Isolated items discarding strategy for discovering high utility itemsets
20. Direct Candidates Generation: A Novel Algorithm for Discovering Complete Share-Frequent Itemsets
21. Complementary-Similarity Learning using Quadruplet Network Walmart Labs
22. Inferring Substitutable Products with Deep Network Embedding IJCAI 2019
23. Item Recommendation on Monotonic Behavior Chains UCSD RecSys 2018
24. Inferring Complementary Products from Baskets and Browsing Yandex Market RecSys 2018
25. Personalized Bundle List Recommendation Alibaba WWW 2019
26. Behavior Sequence Transformer for E-commerce Recommendation in Alibaba Alibaba
27. Temporal Recommendation on Graphs via Long- and Short-term Preference Fusion IBM KDD 2010
28. Don’t Classify, Translate: Multi-Level E-Commerce Product Categorization Via Machine Translation, Video NUS Rakuten
29. Generating and Personalizing Bundle Recommendations on Steam UCSD SIGIR 2017
30. Context-Aware Recommender Systems
31. Basket-Sensitive Personalized Item Recommendation IJCAI 2017
32. Factorizing Personalized Markov Chains for Next-Basket Recommendation WWW2010
33. Learning Hierarchical Representation Model for Next Basket Recommendation SIGIR 2015

Embeddings

1. Meta-Prod2Vec - Product Embeddings Using Side-Information for Recommendation Criteo Facebook RecSys 2016

Price Sensitivity

1. Modeling Consumer Preferences and Price Sensitivities from Large-Scale Grocery Shopping Transaction Logs Microsoft UCSD WWW 2017
2. Personal Price Aware Multi-Seller Recommender System: Evidence from eBay eBay

Miscellaneous

1. How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility Princeton RecSys 2018
2. Explore-Exploit in Top-N Recommender Systems via Gaussian Processes, Video ETH Microsoft Google RecSys 2014

Anamoly/Fraud Detection

1. Isolation Forest Monash University Nanjing University
2. Isolation-based Anomaly Detection - Isolation Forest - Long Paper Monash University Nanjing University TKDD
3. iNNE - Efficient Anomaly Detection by Isolation Using Nearest Neighbour Ensemble Monash University Federation University ICDM-W
4. LOF: Identifying Density-Based Local Outliers University of Munich University of British Columbia SIGMOD 2000
5. Which Anomaly Detector should I use? Federation University Osaka University ICDM 2018
6. PyOD: A Python Toolbox for Scalable Outlier Detection, GitHub CMU University of Toronto Northeastern University Toronto
7. SUOD: A Scalable Unsupervised Outlier Detection Framework, GitHub CMU IQVIA University of Illinois KDD 2020
8. Liar Buyer Fraud, and How to Curb It Zapfraud Inc. NYU UCSD
9. Detecting organized eCommerce fraud using scalable categorical clustering Aalto University
10. A Pattern Based Anti-Fraud Method in C2C Ecommerce Environment Beijing Institute of Technology
11. Microsoft Uses Machine Learning and Optimization to Reduce E-Commerce Fraud Microsoft INFORMS
12. Dual Sequential Variational Autoencoders for Fraud Detection Univ. Lyon Univ. St-Etienne IDA 2020
13. Fraud Detection for E-commerce Transactions by Employing a Prudential Multiple Consensus Model University of Cagliari
14. Adaptive Fraud Detection System Using Dynamic Risk Virginia Tech Microsoft
15. Fraud detection system : A survey Universiti Teknologi Malaysia
16. Graph-based Anomaly Detection and Description: A Survey Stony Brook University City University of New York CMU
17. Temporal Sequence Learning and Data Reduction for Anomaly Detection Purdue
18. A Comprehensive Survey of Data Mining-based Fraud Detection Research Monash University Baycorp Advantage
19. On Identifying Anomalies in Tor Usage with Applications in Detecting Internet Censorship Oxford
20. Temporal Anomaly Detection: Calibrating the Surprise IBM
21. Towards Detecting Anomalous User Behavior in Online Social Networks AT&T Labs Northeastern University

Sampling

1. Active Sampling for Entity Matching with Guarantees Facebook Microsoft Stanford Google
2. iSampling: Framework for Developing Sampling Methods Considering User’s Interest Pohang University of Science and Technology CIKM 2012
3. CGMOS: Certainty Guided Minority OverSampling CIKM 2016
4. Compression-Based Selective Sampling for Learning to Rank Federal University of Minas Gerais CIKM 2016
5. A Personalised Ranking Framework with Multiple Sampling Criteria for Venue Recommendation University of Glasgow CIKM 2017
6. Active Sampling for Large-scale Information Retrieval Evaluation University of Amsterdam CIKM 2017
7. Adaptive Feature Sampling for Recommendation with Missing Content Feature Values Tsinghua University Rutgers University CIKM 2019
8. Efficiently Learning the Accuracy of Labeling Sources for Selective Sampling CMU KDD 2009
9. Active Sampling for Entity Matching Yahoo Stanford
10. Batch Mode Active Sampling based on Marginal Probability Distribution Matching KDD 2012
11. Selective Sampling on Graphs for Classification IBM KDD 2013
12. Sampling for Big Data University of Warwick Texas A&M University KDD 2014
13. On Sampling Strategies for Neural Network-based Collaborative Filtering University of California Yahoo Etsy Inc. KDD 2017
14. Sampling-Bias-Corrected Neural Modeling for Large Corpus Item Recommendations Google KDD 2019

Feature Engineering

1. featuretools
   • Introductory Notebook
   • Video - Featuretools | Machine Learning & Data Science Open-source Spotlight #2, Video - Building online churn prediction ML model using XGBoost, Spark, Featuretools, Python and GCP
   • Video - YOW! Data 2019 - Ananth Gundabattula - Auto feature engineering
2. tsfresh
3. autofeat
4. feature-engine