Amazon
Jump to navigation
Jump to search
Amazon is the largest online retailer as well, with its subsidiary Amazon Web Services (AWS), the largest cloud provider in the Western world. They were also one of the first, if not the first, commercial user of recommendation systems. AWS also offers recommendations as a service with their product AWS Personalize.
Papers
- all search and information retrieval publications by Amazon
- Amazon.com Recommendations: Item-to-Item Collaborative Filtering, IEEE Internet Computing, 2003
- Estimating the Causal Impact of Recommendation Systems from Observational Data, EC 2015
- One-Pass Ranking Models for Low-Latency Product Recommendations, KDD 2015
- 👓 Adaptive, Personalized Diversity for Visual Discovery, RecSys 2016 (best short paper)
- Diversifying Music Recommendations, ICML 2016
- Sustainability at Scale: Towards Bridging the Intention-Behavior Gap with Sustainable Recommendations, RecSys 2017
- Recommending Product Sizes to Customers, RecSys 2017
- 🕴 Two Decades of Recommender Systems at Amazon.com, 2017
- Intent Based Relevance Estimation from Click Logs, CIKM 2017
- MRNet-Product2Vec: A Multi-task Recurrent Neural Network for Product Embeddings, ECML-PKDD 2017
- 📑🎰 Learning to Rank in the Position Based Model with Bandit Feedback (Amazon Music)
- 🎰 A Linear Bandit for Seasonal Environments (Amazon Music)
- An efficient neighborhood-based interaction model for recommendation on heterogeneous graph
- 👓 Adaptive, personalized diversity for visual discovery, RecSys 2016
- 🧠 The Effectiveness of a Two-layer Neural Network for Recommendations, ICLR 2018
- Buy It Again: Modeling Repeat Purchase Recommendations, KDD 2018
- LORE: A Large-Scale Offer Recommendation Engine Through the Lens of an Online Subscription Service
- 🔍 Learning Robust Models for e-Commerce Product Search
- 🔍 Treating Cold Start in Product Search by Priors
- 🏃 Scalable Feature Selection for (Multitask) Gradient Boosted Trees
- 📑 Multi-objective Relevance Ranking via Constrained Optimization
- Language-Agnostic Representation Learning for Product Search on E-Commerce Platforms
- 📄 Whole page optimization with local and global constraints, KDD 2019 (Amazon Video)
- 🏃 Large-scale Collaborative Filtering with Product Embeddings, 2019
- P-Companion: A principled framework for diversified complementary product recommendation, CIKM 2020
- 🔍 Why Do People Buy Seemingly Irrelevant Items in Voice Product Search?, WSDM 2020, blog post
- 🧠 Temporal-Contextual Recommendation in Real-Time, KDD 2020 (best applied data science paper), notes
- Challenges and research opportunities in ecommerce search and recommendations, SIGIR Forum 2020
- A flexible large-scale similar product identification system in e-commerce, KDD 1st International Workshop on Industrial Recommendation 2020
- 📑 CPR: Collaborative pairwise ranking for online list recommendations, RecSys 2020 Workshop on Online Recommender Systems and User Modeling
- 👗 Fashion Outfit Complementary Item Retrieva, CVPR 2020
- Amazon SageMaker Automatic Model Tuning: Scalable Black-box Optimization, 2020
- TabTransformer: Tabular Data Modeling Using Contextual Embeddings, arXiv preprint, 2020
- 🎰 Learning from eXtreme bandit feedback
- 🧠 Heterogeneous graph neural networks with neighbor-SIM attention mechanism for substitute product recommendation, DLG-AAAI 2021
- 🔍 Seasonal relevance in e-commerce search, CIKM 2021
- 👗 Contrastive Learning for Interactive Recommendation in Fashion, SIGIR 2022
- 🔍🔬 N. Bi, P. Castells, D. Gilbert, S. Galperin, P. Tardif, S. Ahuja: Debiased balanced interleaving at Amazon Search, CIKM 2022
Blog posts
- Applying PECOS to product retrieval and text autocompletion, 2021-08-26
- 🧠 🏃 How to train large graph neural networks efficiently, 2021-08-20
- 🕴 The science behind Amazon’s new StyleSnap for Home feature, 2020-12-22
- George Karypis receives ICDM 10-Year-Highest-Impact award (about SLIM), 2020-12-08
- What’s new in recommender systems, 2020-11-17
- 🎰 A general approach to solving bandit problems, 2020-10
- The history of Amazon’s recommendation algorithm, 2019-11-22
- Improving complementary-product recommendations
- CVPR: Deep learning has more gas in the tank
- Amazon publications at CVPR 2020
- 👓 How computer vision will help Amazon customers shop online
Articles about Amazon
Software
- https://github.com/amzn/amazon-dsstne: open source software library for training and deploying recommendation models with sparse inputs, fully connected hidden layers, and sparse outputs. Models with weight matrices that are too large for a single GPU can still be trained on a single host. DSSTNE has been used at Amazon to generate personalized product recommendations for our customers at Amazon’s scale.
