Causal ML estimates supply impact in two-sided marketplaces

This paper introduces a causal machine learning method to estimate the impact of increased supply on outcomes in two-sided marketplaces, such as transaction volume or value. The approach combines double/debiased machine learning with a hierarchical Bayesian framework, using product segment similarity features derived from geospatial literature. Applied to the Airbnb marketplace to assess the effect of additional listings on bookings, the model demonstrated plausible estimates and strong out-of-sample performance. AI

IMPACT Provides a novel methodological framework for analyzing marketplace dynamics using causal machine learning, applicable to various platforms.

RANK_REASON Academic paper detailing a new methodology for causal inference in marketplaces. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• Airbnb

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →