時間：2023年1月5日（周四）上午10:00-11:30
地點(diǎn)：#騰訊會議：116-996-172
報告內(nèi)容簡介:
We develop a machine learning method to mitigate investor irrationality in copy trading. Copy trading allows layman investors (followers) to evaluate and copy expert traders’ transactions. The key challenge faced by followers is choosing which traders to follow. We observe a prevalence of irrationality in follower choices and specifically identify two sources of irrationality: 1) herding due to cognitive load and salient information and 2) bias due to over-reliance on source credibility that is irrelevant to trader performance. We then propose an irrationality-aware machine learning approach to augment followers’ copy-trading decisions by regularizing irrationality in the algorithm’s objective function. This new approach yields superior copy-trading performance, attributed to its ability in mitigating irrationality inherent in human decisions.
報告人簡介:
Zhiqiang (Eric) Zheng is the Ashbel Smith Professor of Information Systems and Finance at the Jindal School of Management, University of Texas at Dallas (UTD). He received his PhD from the Wharton School of Business, University of Pennsylvania. His current research interests focus on FinTech, Blockchain and Digital Asset Management and is a leading scholar in these areas. His papers have appeared in Management Science, MIS Quarterly, Information Systems and Research, Production and Operations Management, among others. Many of his papers have won the best paper award in journals and conferences. He is the founding director of the Center for Fintech and Digital Asset Management at UTD. He has served as a senior editor for Information Systems Research and is the editor for the Fintech and Blockchain special issue. He co-founded the Informs Workshop on Data Science in 2017 and chaired WITS 2022.
（承辦：管理工程系、長三角研究院數(shù)字經(jīng)濟(jì)創(chuàng)新研究中心、科研與學(xué)術(shù)交流中心）
