Modeling Dynamic User Preference for Sequential Recommendation Using Dictionary Learning PROJECT TITLE : Modeling Dynamic User Preference via Dictionary Learning for Sequential Recommendation ABSTRACT: Because users' preferences frequently shift over the course of time, it is essential to accurately capture the dynamics of user preference in order to more accurately predict future user behaviors. It is difficult to combine a user's static preferences with their dynamic ones because many of the existing recommendation algorithms, including both shallow and deep ones, model such dynamics independently. This means that user static preferences and dynamic preferences are not modeled under the same latent space. The problem of embedding a user's sequential behavior into the latent space of user preferences is the focus of this paper. Another name for this problem is "translating sequence to preference." In order to accomplish this, we formulate the sequential recommendation task as a dictionary learning problem. This problem learns: 1) a shared dictionary matrix, where each row represents a partial signal of user dynamic preferences that are shared across users; and 2) a posterior distribution estimator using a deep autoregressive model integrated with Gated Recurrent Unit (GRU), which can select related rows of the dictionary to represent a user's dynamic preferences conditioned on his or her past behavior. In this way, the sequential recommendation task can be Quantitative studies on multiple real-world datasets demonstrate that the proposed method can achieve higher accuracy when compared with state-of-the-art factorization and neural sequential recommendation methods. These studies were conducted using the Netflix dataset. Qualitative studies demonstrated that the proposed method can capture the user preference drifts over time. Did you like this research project? To get this research project Guidelines, Training and Code... Click Here facebook twitter google+ linkedin stumble pinterest More Than Privacy Applying Differential Privacy in Important Aspects of Artificial Intelligence Minority Estimation-based by subregion sampling too much for imbalanced learning