{"title":"Optimal Match Recommendations in Two-sided Marketplaces with Endogenous Prices","authors":"Peng Shi","doi":"10.2139/ssrn.4034950","DOIUrl":null,"url":null,"abstract":"Many two-sided marketplaces rely on match recommendations to help customers find suitable service providers at suitable prices. (Examples include Angi, HomeAdvisor, Thumbtack and To8to.) This paper develops a tractable methodology that a platform can use to optimize its match recommendation policy so as to maximize the total value generated by the platform while accounting for the endogeneity of transaction prices, which are determined by the providers and can depend on the platform's match recommendation policy. Despite the complications due to price endogeneity, an optimal match recommendation policy can be computed efficiently using stochastic subgradient descent. Under additional regularity conditions on the distribution of preferences, an optimal policy has a simple form: for each customer segment and each provider, the platform has a certain target on the rate that the provider is recommended to this segment. Any policy that achieves these targets is optimal. Finally, accounting for the endogeneity of prices is crucial: if the platform were to optimize its match recommendations while erroneously assuming that prices are exogenous, then the market is likely to get stuck at a strictly sub-optimal equilibrium, even if the platform were to continually re-optimize its match recommendation policy after prices re-equilibrate. Link to full paper: https://ssrn.com/abstract=4034950","PeriodicalId":209859,"journal":{"name":"Proceedings of the 23rd ACM Conference on Economics and Computation","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2022-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 23rd ACM Conference on Economics and Computation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2139/ssrn.4034950","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
Many two-sided marketplaces rely on match recommendations to help customers find suitable service providers at suitable prices. (Examples include Angi, HomeAdvisor, Thumbtack and To8to.) This paper develops a tractable methodology that a platform can use to optimize its match recommendation policy so as to maximize the total value generated by the platform while accounting for the endogeneity of transaction prices, which are determined by the providers and can depend on the platform's match recommendation policy. Despite the complications due to price endogeneity, an optimal match recommendation policy can be computed efficiently using stochastic subgradient descent. Under additional regularity conditions on the distribution of preferences, an optimal policy has a simple form: for each customer segment and each provider, the platform has a certain target on the rate that the provider is recommended to this segment. Any policy that achieves these targets is optimal. Finally, accounting for the endogeneity of prices is crucial: if the platform were to optimize its match recommendations while erroneously assuming that prices are exogenous, then the market is likely to get stuck at a strictly sub-optimal equilibrium, even if the platform were to continually re-optimize its match recommendation policy after prices re-equilibrate. Link to full paper: https://ssrn.com/abstract=4034950