Integrated Ranking for News Feed with Reinforcement Learning

With the development of recommender systems, it becomes an increasingly common need to mix multiple item sequences from different sources. Therefore, the integrated ranking stage is proposed to be responsible for this task with re-ranking models. However, existing methods ignore the relation between the sequences, thus resulting in local optimum over the interaction session. To resolve this challenge, in this paper, we propose a new model named NFIRank (News Feed Integrated Ranking with reinforcement learning) and formulate the whole interaction session as a MDP (Markov Decision Process). Sufficient offline experiments are provided to verify the effectiveness of our model. In addition, we deployed our model on Huawei Browser and gained 1.58% improvements in CTR compared with the baseline in online A/B test. Code will be available at https://gitee.com/mindspore/models/tree/master/research/recommend/NFIRank.