Time-sequential variational conditional auto-encoders for recommendation

Abstract

In this study, we propose a method for adding time of action information to a Variational Auto-encoder (VAE)based recommendation system. Since time of action is an important information to improve the accuracy of recommendation, many methods have been proposed to use the information of time of action, such as purchase or review of a product, for recommendation. And VAE-based recommendation systems have been reported to be more accurate and robust for small data sets compared to traditional deep learning-based recommendation systems. Existing research on introducing time information into VAEs includes a method of weaving information on the order in which products are preferred by passing the encoding layer consisting of RNN, but the time information of the product preferred is not considered. If the absolute time information is not taken into account when recommending a product, for example, when a temporary boom causes many users to prefer a particular product, it may be judged to be a preference based on the user’s preferences, which may adversely affect the recommendation results. Based on the above problems, this study examines a VAE-based recommendation system to improve the recommendation accuracy by adding time information of each action to the input information, and finally proposes Time-Sequential VAE (TSVAE) and confirms its accuracy. In addition, to verify how to add time information to improve the accuracy, we conducted experiments using multiple models with and without absolute time information and different encoders of time interval information, and evaluated the accuracy.