Fast ALS-based matrix factorization for explicit and implicit feedback datasets

István Pilászy, Dávid Zibriczky, Domonkos Tikk

Research output: Chapter in Book/Report/Conference proceedingConference contribution

94 Citations (Scopus)

Abstract

Alternating least squares (ALS) is a powerful matrix factor- ization (MF) algorithm for both explicit and implicit feed- back based recommender systems. As shown in many articles, increasing the number of latent factors (denoted by K) boosts the prediction accuracy of MF based recommender systems, including ALS as well. The price of the better accuracy is paid by the increased running time: the running time of the original version of ALS is proportional to K 3. Yet, the running time of model building can be important in recommendation systems; if the model cannot keep up with the changing item portfolio and/or user profile, the predic- tion accuracy can be degraded. In this paper we present novel and fast ALS variants both for the implicit and explicit feedback datasets, which offers better trade-off between running time and accuracy. Due to the significantly lower computational complexity of the algorithm-linear in terms of K-the model being generated under the same amount of time is more accurate, since the faster training enables to build model with more latent factors. We demonstrate the efficiency of our ALS variants on two datasets using two performance measures, RMSE and average relative position (ARP), and show that either a significantly more accurate model can be generated under the same amount of time or a model with similar predic- tion accuracy can be created faster; for explicit feedback the speed-up factor can be even 5-10.

Original languageEnglish
Title of host publicationRecSys'10 - Proceedings of the 4th ACM Conference on Recommender Systems
Pages71-78
Number of pages8
DOIs
Publication statusPublished - Dec 15 2010
Event4th ACM Recommender Systems Conference, RecSys 2010 - Barcelona, Spain
Duration: Sep 26 2010Sep 30 2010

Publication series

NameRecSys'10 - Proceedings of the 4th ACM Conference on Recommender Systems

Other

Other4th ACM Recommender Systems Conference, RecSys 2010
CountrySpain
CityBarcelona
Period9/26/109/30/10

    Fingerprint

Keywords

  • Alternating least squares
  • Collaborative filtering
  • Com-putational complexity
  • Implicit and explicit feedback
  • Matrix factorization
  • Ridge regression

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Software
  • Control and Systems Engineering

Cite this

Pilászy, I., Zibriczky, D., & Tikk, D. (2010). Fast ALS-based matrix factorization for explicit and implicit feedback datasets. In RecSys'10 - Proceedings of the 4th ACM Conference on Recommender Systems (pp. 71-78). (RecSys'10 - Proceedings of the 4th ACM Conference on Recommender Systems). https://doi.org/10.1145/1864708.1864726