Recommender systems are widely used for suggesting books, education materials, and products to users by exploring their behaviors. In reality, users' preferences often change over time, leading to studies on time-dependent recommender systems. However, most existing approaches that deal with time information remain primitive. In this paper, we extend existing methods and propose a hidden semi-Markov model to track the change of users' interests. Particularly, this model allows for capturing the different durations of user stays in a (latent) interest state, which can better model the heterogeneity of user interests and focuses. We derive an expectation maximization algorithm to estimate the parameters of the framework and predict users' actions. Experiments on three real-world datasets show that our model significantly outperforms the state-of-the-art time-dependent and static benchmark methods. Further analyses of the experiment results indicate that the performance improvement is related to the heterogeneity of state durations and the drift of user interests in the dataset.

翻译：推荐系统通过分析用户行为，被广泛应用于为用户推荐书籍、教育资料和产品。现实中，用户的偏好常随时间变化，这推动了时序推荐系统的研究。然而，现有大多数处理时间信息的方法仍较为初级。本文扩展了现有方法，提出一种隐半马尔可夫模型来追踪用户兴趣的变化。该模型尤其能够捕捉用户停留在某个（潜在）兴趣状态的不同时长，从而更好地建模用户兴趣与关注点的异质性。我们推导了期望最大化算法来估计框架参数并预测用户行为。在三个真实数据集上的实验表明，本模型显著优于当前最先进的时序推荐基准方法与静态基准方法。对实验结果的进一步分析表明，性能提升与状态时长的异质性以及数据集中用户兴趣的漂移现象密切相关。