Uncertainty-Calibrated Recommendations for Low-Active Users

2026-05-17

AI Summary

This work addresses the tension in recommendation systems between insufficient reliability for low-activity users and inadequate content diversity for high-activity users by proposing the first unified uncertainty-calibrated framework tailored for industrial-scale short-video and live-streaming platforms. The framework quantifies model uncertainty and applies user-stratified recommendation strategies: a risk-averse down-weighting approach for low-activity users and an upper confidence bound (UCB)-based exploration mechanism that embraces risk for high-activity users. Experimental results demonstrate that the proposed method significantly improves retention duration and viewing satisfaction among low-activity users while effectively enhancing interest diversity and category coverage for high-activity users.

Abstract

A fundamental challenge in recommender systems is balancing reliability for Low-Active Users (LAUs) with diversity for High-Active Users (HAUs). The key to this balance lies in quantifying model uncertainty, which approximates the risk of prediction errors and reveals the limits of the model's current knowledge. On large-scale short-video and livestream platforms, model uncertainty can warn of low-quality recommendations that may lead to disengagement of LAUs and at the same time identify opportunities to diversify content recommendation for HAUs. To leverage this dichotomy, we introduce a unified, production-ready framework that calibrates uncertainty to drive differentiated strategies. Specifically, we implement a model-uncertainty-based risk-averse deboosting policy for LAUs to suppress unreliable recommendations, while employing a risk-seeking Upper Confidence Bound (UCB) strategy for HAUs to encourage exploration. Validated on a major livestream platform, our framework demonstrates significant improvements in retention (active hours) and satisfaction (quality watch time ratio) for LAUs as well as remarkable increases in interest diversity and category coverage for HAUs, proving the value of uncertainty-aware recommendation in industrial settings.

Problem

• recommender systems
• Low-Active Users
• model uncertainty
• recommendation diversity
• user engagement

Innovation

• uncertainty calibration
• low-active users
• risk-averse deboosting
• Upper Confidence Bound
• diversified recommendation