Crowds, Lending, Machine, and Bias

• 成果类型: Article
• 署名作者: Fu, Runshan; Huang, Yan; Singh, Param Vir
• 署名单位: Carnegie Mellon University; Carnegie Mellon University
• 刊物名称: INFORMATION SYSTEMS RESEARCH
• ISSN/ISSBN: 1047-7047
• DOI: 10.1287/isre.2020.0990
• 发表日期: 2021
• 页码: 72-92
• 关键词: credit; RISK; ECONOMICS

摘要

Big data and machine learning (ML) algorithms are key drivers of many fintech innovations. Although it may be obvious that replacing humans with machines would increase efficiency, it is not clear whether and how machines can improve human decisions. We answer this question in the context of crowd lending, in which decisions are traditionally made by a crowd of investors. Using data from Prosper.com, we show that a reasonably sophisticated ML algorithm predicts listing default probability more accurately than crowd investors. The improvement of the machine over the crowd predictions is more pronounced for highly risky listings. We then use the machine to make investment decisions and find that the machine improves upon investors' decisions and leads to greater welfare for both investors and borrowers simultaneously. When machine prediction is used to select loans, it leads to a higher rate of return for investors and more funding opportunities for borrowers with few alternative funding options. We also find suggestive evidence that the machine is biased in gender and race even when it does not use gender and race information as input. We propose a general and effective debiasing method that can be applied to any prediction-focused ML applications and demonstrate its use in our context. We show that the debiased ML algorithm, which suffers from lower prediction accuracy, still improves the crowd's investment decisions in our context. These results indicate that ML can help crowd-lending platforms better fulfill the promise of providing access to financial resources to otherwise underserved individuals and ensure fairness in the allocation of these resources.