Transfer to Rank for Top-N Recommendation

Abstract

In this paper, we study top-N recommendation by exploiting users' explicit feedback such as 5-star numerical ratings, which has been overlooked to some extent in the past decade. As a response, we design a novel and generic transfer learning based recommendation framework coarse-to-fine transfer to rank (CoFiToR), which is a significant extension of a very recent work called transfer to rank (ToR). The key idea of our solution is modeling users' behaviors by simulating users' shopping processes. Therefore, we convert the studied ranking problem to three subtasks corresponding to three specific questions, including (i) whether an item will be examined by a user, (ii) how an item will be scored by a user, and (iii) whether an item will finally be purchased by a user. Based on this new conversion, we then develop a three-staged solution that progressively models users' preferences from a coarse granularity to a fine granularity. In each stage, we adopt an appropriate recommendation algorithm with pointwise or pairwise preference assumption to answer each question in order to seek an effective and efficient overall solution. Empirical studies on two large and public datasets showcase the merits of our solution in comparison with the state-of-the-art methods.

Experience: Analyzing Missing Web Page Visits and Unintentional Web Page Visits from the Client-side Web Logs

“…One way to increase direct purchases and improve users' satisfaction is by designing better recommender algorithms to increase the appearance rate of a user's desired items. This line of research includes contentbased approaches [40], collaborative iltering [9,37,49,56], and hybrid methods (using both content-based and collaborative iltering) [5,16,17,42,45]. Collaborative iltering requires leveraging many users' collective behaviors to determine the relationship between items and users.…”