Revisiting the Performance of iALS on Item Recommendation Benchmarks
This work is incremental, as it revisits and improves an existing method for recommender systems, potentially benefiting researchers and practitioners by enhancing a scalable baseline.
The paper tackled the perceived underperformance of the iALS matrix factorization method in recommender systems by demonstrating that with proper tuning, iALS becomes highly competitive, outperforming other methods on at least half of benchmark comparisons.
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.