Reweighting Clicks with Dwell Time in Recommendation

TL;DR

This paper introduces a method to improve recommendation systems by reweighting user clicks based on dwell time, which better captures true user satisfaction and enhances model performance.

Contribution

It proposes a novel dwell time-based reweighting approach and a new behavior called valid read to select high-quality click data for training.

Findings

Significant improvements in offline recommendation accuracy.

Enhanced online system performance.

Effective filtering of low-quality clicks using dwell time.

Abstract

The click behavior is the most widely-used user positive feedback in recommendation. However, simply considering each click equally in training may suffer from clickbaits and title-content mismatching, and thus fail to precisely capture users' real satisfaction on items. Dwell time could be viewed as a high-quality quantitative indicator of user preferences on each click, while existing recommendation models do not fully explore the modeling of dwell time. In this work, we focus on reweighting clicks with dwell time in recommendation. Precisely, we first define a new behavior named valid read, which helps to select high-quality click instances for different users and items via dwell time. Next, we propose a normalized dwell time function to reweight click signals in training for recommendation. The Click reweighting model achieves significant improvements on both offline and online evaluations in real-world systems.