From Generation to Consumption: Personalized List Value Estimation for Re-ranking

TL;DR

This paper introduces CAVE, a novel re-ranking framework that models user exit behavior to better estimate the actual value of recommendation lists, leading to improved performance.

Contribution

CAVE is the first framework to explicitly incorporate user exit probabilities into list value estimation for re-ranking.

Findings

CAVE outperforms strong baselines on multiple benchmarks.

Modeling user exit behavior improves recommendation accuracy.

Online A/B tests show increased user satisfaction and revenue.

Abstract

Re-ranking is critical in recommender systems for optimizing the order of recommendation lists, thus improving user satisfaction and platform revenue. Most existing methods follow a generator-evaluator paradigm, where the evaluator estimates the overall value of each candidate list. However, they often ignore the fact that users may exit before consuming the full list, leading to a mismatch between estimated generation value and actual consumption value. To bridge this gap, we propose CAVE, a personalized Consumption-Aware list Value Estimation framework. CAVE formulates the list value as the expectation over sub-list values, weighted by user-specific exit probabilities at each position. The exit probability is decomposed into an interest-driven component and a stochastic component, the latter modeled via a Weibull distribution to capture random external factors such as fatigue. By jointly modeling sub-list values and user exit behavior, CAVE yields a more faithful estimate of actual list consumption value. We further contribute three large-scale real-world list-wise benchmarks from the Kuaishou platform, varying in size and user activity patterns. Extensive experiments on these benchmarks, two Amazon datasets, and online A/B testing on Kuaishou show that CAVE consistently outperforms strong baselines, highlighting the benefit of explicitly modeling user exits in re-ranking.