Causality-Aware Neighborhood Methods for Recommender Systems

TL;DR

This paper introduces a causality-aware neighborhood recommendation method using matching estimators, which improves causal effect estimation and outperforms existing methods in ranking metrics, leading to increased sales and engagement.

Contribution

It unifies neighborhood recommendation with matching estimators to develop robust causal effect ranking methods, addressing high variance issues in inverse propensity scoring.

Findings

Proposed methods outperform baselines in causal ranking metrics

Methods lead to increased sales and user engagement

Robustness against high variance in causal inference

Abstract

The business objectives of recommenders, such as increasing sales, are aligned with the causal effect of recommendations. Previous recommenders targeting for the causal effect employ the inverse propensity scoring (IPS) in causal inference. However, IPS is prone to suffer from high variance. The matching estimator is another representative method in causal inference field. It does not use propensity and hence free from the above variance problem. In this work, we unify traditional neighborhood recommendation methods with the matching estimator, and develop robust ranking methods for the causal effect of recommendations. Our experiments demonstrate that the proposed methods outperform various baselines in ranking metrics for the causal effect. The results suggest that the proposed methods can achieve more sales and user engagement than previous recommenders.