Inferring Networks of Substitutable and Complementary Products

Abstract

In a modern recommender system, it is important to understand how products relate to each other. For example, while a user is looking for mobile phones, it might make sense to recommend other phones, but once they buy a phone, we might instead want to recommend batteries, cases, or chargers. These two types of recommendations are referred to as substitutes and complements: substitutes are products that can be purchased instead of each other, while complements are products that can be purchased in addition to each other. Here we develop a method to infer networks of substitutable and complementary products. We formulate this as a supervised link prediction task, where we learn the semantics of substitutes and complements from data associated with products. The primary source of data we use is the text of product reviews, though our method also makes use of features such as ratings, specifications, prices, and brands. Methodologically, we build topic models that are trained to automatically discover topics from text that are successful at predicting and explaining such relationships. Experimentally, we evaluate our system on the Amazon product catalog, a large dataset consisting of 9 million products, 237 million links, and 144 million reviews.

arXiv comment12 pages, 6 figures

References in corpus (1)

• Supervised Topic Models

Cited by in corpus (36)

• Learning to Generate Reviews and Discovering Sentiment
• Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec
• A Large Self-Annotated Corpus for Sarcasm
• Joint Deep Modeling of Users and Items Using Reviews for Recommendation
• Network Structure Inference, A Survey: Motivations, Methods, and Applications
• A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks
• Learning Compatibility Across Categories for Heterogeneous Item Recommendation
• TransRev: Modeling Reviews as Translations from Users to Items
• Modeling Visual Compatibility through Hierarchical Mid-level Elements
• Inferring Complementary Products from Baskets and Browsing Sessions
• Don't Classify, Translate: Multi-Level E-Commerce Product Categorization Via Machine Translation
• DenseAlert: Incremental Dense-Subtensor Detection in Tensor Streams
• Discrete Factorization Machines for Fast Feature-based Recommendation
• Portrait of an Online Shopper: Understanding and Predicting Consumer Behavior
• CER: Complementary Entity Recognition via Knowledge Expansion on Large Unlabeled Product Reviews
• Large Scale Product Graph Construction for Recommendation in E-commerce
• Disentangling Aspect and Opinion Words in Target-based Sentiment Analysis using Lifelong Learning
• Evaluating Social Networks Using Task-Focused Network Inference
• Mining Compatible/Incompatible Entities from Question and Answering via Yes/No Answer Classification using Distant Label Expansion
• Supervised Complementary Entity Recognition with Augmented Key-value Pairs of Knowledge
• Recommendation Through Mixtures of Heterogeneous Item Relationships
• Complete the Look: Scene-based Complementary Product Recommendation
• KeystoneML: Optimizing Pipelines for Large-Scale Advanced Analytics
• "Are you sure?": Preliminary Insights from Scaling Product Comparisons to Multiple Shops
• MV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation
• Robust reputation-based ranking on multipartite rating networks
• Linked Causal Variational Autoencoder for Inferring Paired Spillover Effects
• Online Product Feature Recommendations with Interpretable Machine Learning
• Recommending Complementary Products in E-Commerce Push Notifications with a Mixture Model Approach
• Sampling Online Social Networks by Random Walk with Indirect Jumps
• Mining Worse and Better Opinions. Unsupervised and Agnostic Aggregation of Online Reviews
• Augmenting the User-Item Graph with Textual Similarity Models
• Mining Contrasting Quasi-Clique Patterns
• A Novel Large-scale Ordinal Regression Model
• Dual Attention Network for Product Compatibility and Function Satisfiability Analysis
• Attentive Long Short-Term Preference Modeling for Personalized Product Search