A Multi-Latent Transition model for evolving preferences in recommender systems
作者：
Highlights：
• We capture user preferences dynamics based on a multi-latent analysis.
• We design a joint objective function and we propose an efficient optimization algorithm.
• We evaluate our method on 2 extended benchmark datasets that span 3 and 4.5 years.
• Our model outperforms baselines for users with stable and dynamic preferences.
• The extended datasets of MovieLens-1M and Last.fm-1K are made publicly available.
摘要
•We capture user preferences dynamics based on a multi-latent analysis.•We design a joint objective function and we propose an efficient optimization algorithm.•We evaluate our method on 2 extended benchmark datasets that span 3 and 4.5 years.•Our model outperforms baselines for users with stable and dynamic preferences.•The extended datasets of MovieLens-1M and Last.fm-1K are made publicly available.
论文关键词：Recommender systems,Preference dynamics,Multi-latent analysis
论文评审过程：Received 24 October 2017, Revised 12 February 2018, Accepted 19 March 2018, Available online 20 March 2018, Version of Record 23 March 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.03.033
