Search

Rating-only collaborative filtering has been extensively studied for decades with great improvements achieved in predicting a user’s preference on a target item at a particular time point. Yet, it remains a research challenge on how to capture users’ rating patterns which may drift over time. In this article, we propose a time-aware matrix co-factorization model, called PCCF , which considers two types of temporal effects, i.e., periodic and continual . Specifically, periodic effects refer to the impact of discrete periodic time slices with which users’ preferences may be associated, and continual effects refer to the impact of continuous gradual time over which users’ preference patterns may change. The fact that users exhibit different preference patterns with respect to different time aspect has been further confirmed by our analysis on three real-world data sets. Together with time-based user biases, we integrate the two kinds of temporal effects into a unified matrix factorization model. Experimental results on the three data sets demonstrate the effectiveness of both kinds of temporal effects for rating prediction as well as the superiority of our approach’s performance over that of the other counterparts. [ABSTRACT FROM AUTHOR]

Personalized recommendation for online service systems aims to predict potential demand by analysing user preference. User preference can be inferred from heterogeneous implicit feedback (i.e. various user actions) especially when explicit feedback (i.e. ratings) is not available. However, most methods either merely focus on homogeneous implicit feedback (i.e. target action), e.g., purchase in shopping websites and forward in Twitter, or dispose heterogeneous implicit feedback without the investigation of its speciality. In this paper, we adopt two typical actions in online service systems, i.e., view and like , as auxiliary feedback to enhance recommendation performance, whereby we propose a Bayesian personalized ranking method for heterogeneous implicit feedback (BPRH). Specifically, items are first classified into different types according to the actions they received. Then by analysing the co-occurrence of different types of actions, which is one of the fundamental speciality of heterogeneous implicit feedback systems, we quantify their correlations, based on which the difference of users’ preference among different types of items is investigated. An adaptive sampling strategy is also proposed to tackle the unbalanced correlation among different actions. Extensive experimentation on three real-world datasets demonstrates that our approach significantly outperforms state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]