Unbiased Platform-Level Causal Estimation for Search Systems: A Competitive Isolation PSM-DID Framework
This work addresses platform-level causal inference for search systems, offering a solution to systemic biases in two-sided marketplaces, though it is incremental as it builds on existing PSM-DID methods.
The paper tackled the problem of evaluating platform-level interventions in search-based marketplaces by addressing systemic effects like spillovers and network interference, resulting in a novel framework that significantly reduces interference effects and estimation variance, with successful deployment in a large-scale marketplace.
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.