Pareto-based Multi-Objective Recommender System with Forgetting Curve

TL;DR

This paper introduces PMORS, a multi-objective recommender system that incorporates a forgetting curve to better handle negative feedback, improving recency and performance in short-video platforms.

Contribution

It proposes a novel Pareto-based optimization method combined with a forgetting model based on Ebbinghaus curve for enhanced recommendation quality.

Findings

Superior performance on public and industrial datasets.

Improved recency and consistency in recommendations.

Up to +1.45% GMV increase after deployment.

Abstract

Recommender systems with cascading architecture play an increasingly significant role in online recommendation platforms, where the approach to dealing with negative feedback is a vital issue. For instance, in short video platforms, users tend to quickly slip away from candidates that they feel aversive, and recommender systems are expected to receive these explicit negative feedbacks and make adjustments to avoid these recommendations. Considering recency effect in memories, we propose a forgetting model based on Ebbinghaus Forgetting Curve to cope with negative feedback. In addition, we introduce a Pareto optimization solver to guarantee a better trade-off between recency and model performance. In conclusion, we propose Pareto-based Multi-Objective Recommender System with forgetting curve (PMORS), which can be applied to any multi-objective recommendation and show sufficiently superiority when facing explicit negative feedback. We have conducted evaluations of PMORS and achieved favorable outcomes in short-video scenarios on both public dataset and industrial dataset. After being deployed on an online short video platform named WeChat Channels in May, 2023, PMORS has not only demonstrated promising results for both consistency and recency but also achieved an improvement of up to +1.45% GMV.