Counterfactual Evaluation of Slate Recommendations with Sequential Reward Interactions

TL;DR

This paper introduces a new counterfactual evaluation method for sequential slate recommendations that reduces variance and relaxes independence assumptions, improving bias and data efficiency.

Contribution

A novel counterfactual estimator for sequential rewards that leverages causal graphical assumptions to improve evaluation accuracy in recommendation systems.

Findings

Outperforms existing methods in simulation tests.

Achieves lower bias in reward estimation.

Demonstrates improved data efficiency in live system.

Abstract

Users of music streaming, video streaming, news recommendation, and e-commerce services often engage with content in a sequential manner. Providing and evaluating good sequences of recommendations is therefore a central problem for these services. Prior reweighting-based counterfactual evaluation methods either suffer from high variance or make strong independence assumptions about rewards. We propose a new counterfactual estimator that allows for sequential interactions in the rewards with lower variance in an asymptotically unbiased manner. Our method uses graphical assumptions about the causal relationships of the slate to reweight the rewards in the logging policy in a way that approximates the expected sum of rewards under the target policy. Extensive experiments in simulation and on a live recommender system show that our approach outperforms existing methods in terms of bias and data efficiency for the sequential track recommendations problem.