Date & Time: July 2, 2025 9:00-11:30
Venue:Meeting Room 1425, Engineering Management & Intelligent Manufacturing Research Center
Speaker:Hongwei Zhu
Institution:University of Massachusetts Lowell
Organizer:School of Management, Hefei University of Technology
Abstract:
Investor psychology provides an important avenue for modeling non-fundamental behaviors in financial analysis. A burgeoning number of machine learning algorithms have been developed to test the effectiveness of investor psychology in market predictions. With all the merits of machine learning approach, it often suffers from issues such as biases, overfitting, and poor performance. To address these issues, we developed a DeepPsych system to harness the power of high frequency market psychology data for trend prediction. In a “hybridization–generalization–dual-channel-fusion” three-stage experiment, we evaluate each proposed module and the entire framework against the state-of-art machine learning benchmarks on investor psychology and trading data of the SPY (SP500 ETF). Results demonstrate that our deep learning framework can significantly improve prediction and support profitable trading.
Biography:
Hongwei Zhu is a professor of Management Information Systems in the Operations and Information Systems Department at the University of Massachusetts Lowell. His research focuses on data quality, analytics and AI, with business applications in areas such as finance and accounting. His work has appeared in MIT Sloan Management Review, Journal of Management Information Systems, Information Systems Research, and transactions and journals of ACM and IEEE. He is an associate editor of the ACM Journal of Data and Information Quality.