Re-ranking With Constraints on Diversified Exposures for Homepage Recommender System

TL;DR

This paper introduces a two-stage homepage recommender system that optimizes for click-through rate and display diversity by combining channel recommendation algorithms with a hierarchical attention-based re-ranking model.

Contribution

It proposes a novel two-stage architecture and a Deep  Hierarchical Attention Network for improved diversity and mutual influence modeling in homepage recommendations.

Findings

Significant improvement in CTR and ILAD in online systems.

Enhanced precision and channel-wise accuracy in offline experiments.

Effective balancing of recommendation relevance and display diversity.

Abstract

The homepage recommendation on most E-commerce applications places items in a hierarchical manner, where different channels display items in different styles. Existing algorithms usually optimize the performance of a single channel. So designing the model to achieve the optimal recommendation list which maximize the Click-Through Rate (CTR) of whole homepage is a challenge problem. Other than the accuracy objective, display diversity on the homepage is also important since homogeneous display usually hurts user experience. In this paper, we propose a two-stage architecture of the homepage recommendation system. In the first stage, we develop efficient algorithms for recommending items to proper channels while maintaining diversity. The two methods can be combined: user-channel-item predictive model with diversity constraint. In the second stage, we provide an ordered list of items in each channel. Existing re-ranking models are hard to describe the mutual influence between items in both intra-channel and inter-channel. Therefore, we propose a Deep \& Hierarchical Attention Network Re-ranking (DHANR) model for homepage recommender systems. The Hierarchical Attention Network consists of an item encoder, an item-level attention layer, a channel encoder and a channel-level attention layer. Our method achieves a significant improvement in terms of precision, intra-list average distance(ILAD) and channel-wise Precision@k in offline experiments and in terms of CTR and ILAD in our online systems.