Where to Explore: A Reach and Cost-Aware Approach for Unbiased Data Collection in Recommender Systems

TL;DR

This paper presents a reach and cost-aware exploration method for recommender systems that safely collects unbiased data at scale, improving long-term recommendations without harming short-term business metrics.

Contribution

It introduces a novel, deployable approach that conditions exploration on low-cost, high-reach UI positions, enhancing data collection and recommendation quality.

Findings

Preserves platform watch time during exploration

Collects unbiased interaction data at scale

Improves downstream recommendation performance

Abstract

Exploration is essential to improve long-term recommendation quality, but it often degrades short-term business performance, especially in remote-first TV environments where users engage passively, expect instant relevance, and offer few chances for correction. This paper introduces an approach for delivering content-level exploration safely and efficiently by optimizing its placement based on reach and opportunity cost. Deployed on a large-scale streaming platform with over 100 million monthly active users, our approach identifies scroll-depth regions with lower engagement and strategically introduces a dedicated container, the "Something Completely Different" row containing randomized content. Rather than enforcing exploration uniformly across the user interface (UI), we condition its appearance on empirically low-cost, high-reach positions to ensure minimal tradeoff against platform-level watch time goals. Extensive A/B testing shows that this strategy preserves business metrics while collecting unbiased interaction data. Our method complements existing intra-row diversification and bandit-based exploration techniques by introducing a deployable, behaviorally informed mechanism for surfacing exploratory content at scale. Moreover, we demonstrate that the collected unbiased data, integrated into downstream candidate generation, significantly improves user engagement, validating its value for recommender systems.