CHINESE
Current Position: Home» News Center» Seminar News»

【Mingli Lecture 2023, Issue 1】Professor Zhiqiang (Eric) Zheng, University of Texas, Dallas, USA: A Machine Learning Approach to Mitiga

Professor Zhiqiang Zheng, Jindal School of Management, University of Texas, Dallas, was invited to give an academic report

Contributed by, Photographer: Department of Management Engineering

At the invitation of the School of Management and Economics, Professor Zhiqiang Zheng of the Jindal School of Management at the University of Texas, Dallas, USA, made an academic report entitled "A Machine Learning Approach to Mitigating Irrationality in Copy Trading" online at 10 a.m. on January 5, 2023. The seminar was hosted by Professor Yan Zhijun and attended by many teachers and students of the college."Copy trading" refers to the practice of non-professional traders (followers) choosing to follow those traders who usually have more experience and higher success rate and reproduce their trading behavior. Professor Zheng first introduced the relevant background of replication trading, and pointed out that there is a common phenomenon of followers' irrational decision-making in the replication trading platform. For example, the followers' following decisions have caused their own return to decline. This irrationality comes from the herding effect caused by cognitive load and relevant information on the one hand, and the decision deviation caused by excessive dependence on identity information irrelevant to the performance of traders on the other hand. Because machine learning method has the advantages of being good at rational decision-making and good prediction performance, it is also suitable for financial technology and trading fields because of its good explanatory ability. Therefore, if machine learning method is combined with artificial decision-making, it can better eliminate the irrationality in the follower's decision-making process. In view of this research background, Professor Zheng and his research team put forward an innovative machine learning algorithm, RXGBoost Contract Method, based on the irrational factors that affect the follower and the contraction process theory, and carried out relevant mechanism analysis. The algorithm improves the follower's copy trading decision by regularizing irrationality in the objective function. This new method helps to perceive and alleviate the irrationality of investors in replication transactions, resulting in excellent decision-making performance.

After the report, the participating teachers and students had a positive and full discussion with Professor Zheng. The report received a warm response and was unanimously praised by teachers and students.

Profile of Professor Zhiqiang Zheng:

Zhiqiang (Eric) Zheng is Professor Ashbel Smith, Department of Information Systems and Finance, Jindal School of Management, University of Texas, Dallas, USA. He received his doctorate from the Wharton School of Business at the University of Pennsylvania. His current research interests focus on financial technology, blockchain and digital asset management, and he is a leading scholar in this field. His papers have been published in Management Science, MIS Quarterly, Information Systems and Research, Production and Operations Management, etc. In addition, many of his papers have won the Best Paper Award in journals and conferences. At the same time, he is the founding director of UTD Financial Technology and Digital Asset Management Center. He was the senior editor of Information Systems and Research and the editor of the special issue of Financial Technology and Blockchain. He co-founded the Workshop of Informs Data Science in 2001 and hosted the WITS conference in 2022.