Sequential Evaluation and Generation Framework for Combinatorial Recommender System
This addresses the challenge of optimizing item correlations in recommender systems for users, but it is incremental as it builds on existing methods with new model architectures and learning metrics.
The paper tackles the problem of combinatorial recommendation by modeling it as generating an ordered sequence of items to maximize expected overall utility, such as total clicks, and proposes an Evaluation-Generation framework that shows an obvious increase in performance compared to previous solutions.
In the combinatorial recommender systems, multiple items are fed to the user at one time in the result page, where the correlations among the items have impact on the user behavior. In this work, we model the combinatorial recommendation as the problem of generating a sequence(ordered list) of items from a candidate set, with the target of maximizing the expected overall utility(e.g. total clicks) of the sequence. Toward solving this problem, we propose the Evaluation-Generation framework. On the one hand of this framework, an evaluation model is trained to evaluate the expected overall utility, by fully considering the user, item information and the correlations among the co-exposed items. On the other hand, generation policies based on heuristic searching or reinforcement learning are devised to generate potential high-quality sequences, from which the evaluation model select one to expose. We propose effective model architectures and learning metrics under this framework. We also offer series of offline tests to thoroughly investigate the performance of the proposed framework, as supplements to the online experiments. Our results show obvious increase in performance compared with the previous solutions.