Metadata Embeddings for User and Item Cold-start Recommendations

Abstract

I present a hybrid matrix factorisation model representing users and items as linear combinations of their content features' latent factors. The model outperforms both collaborative and content-based models in cold-start or sparse interaction data scenarios (using both user and item metadata), and performs at least as well as a pure collaborative matrix factorisation model where interaction data is abundant. Additionally, feature embeddings produced by the model encode semantic information in a way reminiscent of word embedding approaches, making them useful for a range of related tasks such as tag recommendations.

References in corpus (3)

• Efficient Estimation of Word Representations in Vector Space
• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Experiments with Random Projection

Cited by in corpus (22)

• Meta-Prod2Vec - Product Embeddings Using Side-Information for Recommendation
• RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms
• Visually-Aware Fashion Recommendation and Design with Generative Image Models
• Predicting IPv4 Services Across All Ports
• Temporal Learning and Sequence Modeling for a Job Recommender System
• Multimodal Data Fusion in High-Dimensional Heterogeneous Datasets via Generative Models
• Exploring Customer Price Preference and Product Profit Role in Recommender Systems
• Unbiased Recommender Learning from Missing-Not-At-Random Implicit Feedback
• Automatic playlist continuation using a hybrid recommender system combining features from text and audio
• Consistent and Flexible Selectivity Estimation for High-Dimensional Data
• A Sequential Embedding Approach for Item Recommendation with Heterogeneous Attributes
• WMRB: Learning to Rank in a Scalable Batch Training Approach
• Deep Determinantal Point Processes
• AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding
• An Analysis of Approaches Taken in the ACM RecSys Challenge 2018 for Automatic Music Playlist Continuation
• Towards Amortized Ranking-Critical Training for Collaborative Filtering
• Attribute-aware Collaborative Filtering: Survey and Classification
• MFAI: A Scalable Bayesian Matrix Factorization Approach to Leveraging Auxiliary Information
• Five lessons from building a deep neural network recommender
• A Hybrid Recommender System for Patient-Doctor Matchmaking in Primary Care
• New Recommendation Algorithm for Implicit Data Motivated by the Multivariate Normal Distribution
• Deep neural network marketplace recommenders in online experiments