Revisiting the Performance of iALS on Item Recommendation Benchmarks

2021/10/26 by Steffen Rendle, Rendle, Steffen, Walid Krichene +5 · 8 citations
Computer Science · #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Recommender Systems and Techniques #Sentiment Analysis and Opinion Mining #Text and Document Classification Technologies

paper · pdf · doi:10.48550/arxiv.2110.14037

openalex publication_date 2021/10/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Matrix factorization learned by implicit alternating least squares (iALS) is a popular baseline in recommender system research publications. iALS is known to be one of the most computationally efficient and scalable collaborative filtering methods. However, recent studies suggest that its prediction quality is not competitive with the current state of the art, in particular autoencoders and other item-based collaborative filtering methods. In this work, we revisit the iALS algorithm and present a bag of tricks that we found useful when applying iALS. We revisit four well-studied benchmarks where iALS was reported to perform poorly and show that with proper tuning, iALS is highly competitive and outperforms any method on at least half of the comparisons. We hope that these high quality results together with iALS's known scalability spark new interest in applying and further improving this decade old technique.

Cited by

• Accurate and Diverse Recommendations via Propensity-Weighted Linear Autoencoders
• Q3R: Quadratic Reweighted Rank Regularizer for Effective Low-Rank Training
• Reproducibility in Recommender Systems: A Survey
• Does Weighting Improve Matrix Factorization for Recommender Systems?
• Efficient Item ID Generation for Large-Scale LLM-based Recommendation
• What Data is Really Necessary? A Feasibility Study of Inference Data Minimization for Recommender Systems
• Leveraging Geometric Insights in Hyperbolic Triplet Loss for Improved Recommendations
• Discrete-event Tensor Factorization: Learning a Smooth Embedding for Continuous Domains

Related

• Fast Matrix Factorization for Online Recommendation with Implicit Feedback
• Fair Matrix Factorisation for Large-Scale Recommender Systems
• Safe Collaborative Filtering
• Data augmentation and refinement for recommender system: A semi-supervised approach using maximum margin matrix factorization
• Alternating Linear Bandits for Online Matrix-Factorization Recommendation