Experimental Design in One-sided Matching Platforms

51 Pages Posted: 12 Jul 2024

See all articles by Chenran Weng

Chenran Weng

University of California, Berkeley - Department of Industrial Engineering and Operations Research

Xiao Lei

HKU Business School, The University of Hong Kong

Nian Si

University of Chicago - Booth School of Business

Date Written: July 10, 2024

Abstract

We investigate experimental design problems in one-sided matching platforms, which are commonly found in the online gaming industry and anonymous social networks. These platforms involve users being matched with others for activities such as games or social interactions, resulting in an interdependence of users' metrics on the treatment assignments of their counterparts. We construct a stochastic market model and develop its mean field limit to analyze the experimental dynamics in such platforms. Our focus is on two randomization strategies: user randomization and match randomization. We demonstrate that under Markovian user behavior and homogeneous treatment effects, match randomization can provide unbiased estimations. However, significant biases may arise when these conditions are not met. On the other hand, user randomization is generally biased but exhibits greater resilience to model inaccuracies. We then propose a simple linear regression estimator under user randomization and demonstrate that this estimator consistently outperforms alternatives in various situations.

Keywords: design of experiments, one-sided platforms

Suggested Citation

Weng, Chenran and Lei, Xiao and Si, Nian, Experimental Design in One-sided Matching Platforms (July 10, 2024). Available at SSRN: https://ssrn.com/abstract=4890353 or http://dx.doi.org/10.2139/ssrn.4890353

Chenran Weng

University of California, Berkeley - Department of Industrial Engineering and Operations Research ( email )

Xiao Lei (Contact Author)

HKU Business School, The University of Hong Kong ( email )

Hong Kong
China

HOME PAGE: http://www.xiao-lei.org

Nian Si

University of Chicago - Booth School of Business ( email )

5807 S. Woodlawn Avenue
Chicago, IL 60637
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
62
Abstract Views
200
Rank
664,140
PlumX Metrics