Interest Changes: Considering User Interest Life Cycle in Recommendation System

TL;DR

This paper introduces DILN, a novel deep learning model that captures user interest life-cycle phases to improve recommendation accuracy and user engagement, demonstrated through significant online performance gains.

Contribution

The paper proposes DILN, a new method that models user interest life-cycle features and integrates them into ranking models, enhancing recommendation relevance.

Findings

DILN improves CTR by 0.38% in online tests.

DILN increases user engagement metrics such as CVR and duration.

DILN effectively emphasizes emergent and stable interests while reducing focus on declining interests.

Abstract

In recommendation systems, user interests are always in a state of constant flux. Typically, a user interest experiences a emergent phase, a stable phase, and a declining phase, which are referred to as the "user interest life-cycle". Recent papers on user interest modeling have primarily focused on how to compute the correlation between the target item and user's historical behaviors, without thoroughly considering the life-cycle features of user interest. In this paper, we propose an effective method called Deep Interest Life-cycle Network (DILN), which not only captures the interest life-cycle features efficiently, but can also be easily integrated to existing ranking models. DILN contains two key components: Interest Life-cycle Encoder Module constructs historical activity histograms of the user interest and then encodes them into dense representation. Interest Life-cycle Fusion Module injects the encoded dense representation into multiple expert networks, with the aim of enabling the specific phase of interest life-cycle to activate distinct experts. Online A/B testing reveals that DILN achieves significant improvements of +0.38% in CTR, +1.04% in CVR and +0.25% in duration per user, which demonstrates its effectiveness. In addition, DILN inherently increase the exposure of users' emergent and stable interests while decreasing the exposure of declining interests. DILN has been deployed on the Lofter App.