Market Outcomes under Different Recommender Systems: Experimental Evidence from an Online Dating Service
How to cite
Hsieh, Yuwei; Lin, Ming-Jen; Chen, Kuan-Ming. 2019. "Market Outcomes under Different Recommender Systems: Experimental Evidence from an Online Dating Service." AEA RCT Registry. AEARCTR-0004211. https://doi.org/10.1257/rct.4211-1.0
Download: BibTeX · RIS — for reference managers without a browser translator. Zotero and most others pick up this page's citation metadata directly.
* Primary investigator
Abstract
We partner with an online dating service to study the market outcomes and consumer behaviors under different recommender systems. There are two treatment groups: The first treatment group receives the recommendation based on the mate preference estimated from the existing database. The second treatment group receives the recommendation based on the same preference estimation, adjusting for the matching cost implied by a structural matching model. The control group receives a randomized recommendation. We measure several outcomes: consumer satisfactory (from a survey after the experimental period), click-through rate, response rate, time to find a dating partner, cross-sectional distribution of the number of likes, degree, and centrality of the dating bipartite graph.
Experimental design
We divide our sample into different groups. Control group implements the default algorithm, while the treatment group implements our recommendation system.
Design details
Cited by
No citation data available for this registration yet.