Unbiased Platform-Level Causal Estimation for Search Systems: A Competitive Isolation PSM-DID Framework

TL;DR

This paper introduces a new causal inference framework, Competitive Isolation PSM-DID, that accurately estimates platform-level effects in search systems by reducing bias and interference, validated through experiments and real-world deployment.

Contribution

It presents a novel causal framework combining propensity score matching with competitive isolation, enabling unbiased platform-level effect estimation under certain conditions.

Findings

Significant reduction in interference effects compared to baseline methods

The framework achieves lower estimation variance

Successful deployment in a large-scale marketplace confirms practical utility

Abstract

Evaluating platform-level interventions in search-based two-sided marketplaces is fundamentally challenged by systemic effects such as spillovers and network interference. While widely used for causal inference, the PSM (Propensity Score Matching) - DID (Difference-in-Differences) framework remains susceptible to selection bias and cross-unit interference from unaccounted spillovers. In this paper, we introduced Competitive Isolation PSM-DID, a novel causal framework that integrates propensity score matching with competitive isolation to enable platform-level effect measurement (e.g., order volume, GMV) instead of item-level metrics in search systems. Our approach provides theoretically guaranteed unbiased estimation under mutual exclusion conditions, with an open dataset released to support reproducible research on marketplace interference (github.com/xxxx). Extensive experiments demonstrate significant reductions in interference effects and estimation variance compared to baseline methods. Successful deployment in a large-scale marketplace confirms the framework's practical utility for platform-level causal inference.