FinTechOverviewRecent years have witnessed a rapidly development in FinTech, or financial technologies, which have been reshaping business practices and the financial services industry. On the other hand, emerging technologies including deep learning, machine learning and big data methods, have also been increasingly applied in the study of financial economics. Such developments have generated considerable interests in the new and important research area of FinTech and emerging technologies. His research topics related to FinTech includes:
Representative work
"Charting By Machines", with Scott Murray and Yusen Xia, Aug. 2022. Revision Requested.
We test the efficient markets hypothesis by using machine learning to forecast future stock returns from historical price plots. These forecasts strongly predict the cross section of future stock returns. The predictive power holds in most subperiods, is strong among the largest 500 stocks, and is distinct from momentum and reversal. The forecasting relation is highly non-linear and remarkably stable through time. Our research design ensures that our findings are not a result of data mining. Our results question the efficient markets hypothesis and indicate that investment strategies based on technical analysis and charting may have merit.
"Can Machines Understand Human Decisions? Dissecting Stock Forecasting Skill", with Sean Cao, Xuxi Guo and Baozhong Yang, 2022.
Semi-finalist of the FMA 2021 Best Paper in FinTech We use machine learning (ML) to provide a novel methodology to determine analysts' skills and effectively aggregate the forecasting opinions of analysts to form a crowd wisdom-based earnings forecast. Our machine-identified skilled analysts persistently outperform expert-picked star analysts. We find that machines rely on nonlinear interactions of analyst characteristics, such as past skill and efforts, to make predictions, unlike human experts, who lean more on relation-based information such as brokerage size.
Slides
Deep Learning
CNN
Big Data
Artificial Intelligence
Analyst Forecast
Analyst Skill
Crowd Wisdom
"From Words to Syntax: Identifying Context-specific Information in Textual Analysis", with Sean Cao, Angie Wang and Yongtae Kim, 2021.
We introduces a novel approach to incorporate complex syntactical features (i.e., the context, sequence of words, and their relationships) in textual analysis using machine learning techniques. We demonstrate the usefulness of this approach by analyzing the tone of financial narratives in earnings conference calls. We construct a new measure of sentiment that is specific to performance discussions and is adjusted for complex contextual negations. We find that this performance-specific sentiment explains cross-sectional returns and future operating performance better than the umbrella sentiment proxy and the simple rule-based measures used in the literature. An analysis of earnings-related forward-looking statements in conference calls confirms the value of this new approach in identifying context-specific information.
Slides
Machine Learning
Textual Analysis
Natural Language Processing
Artificial Intelligence
Sentiment Analysis
Conference Calls
"Resolving Conflicts in Crowds: A Earnings Forecasts Application", 2022. Submited.
We presents a novel and effective optimization-based approach to resolve such conflicts in earnings forecast data and generate an accurate and robust earnings forecast consensus. Consistent with the wisdom-of-crowds effect, the new earnings forecast consensus is more accurate than the Wall Street consensus (67.5%) and IBES consensus (67.4%) of the time. The new earnings forecast consensus are incrementally useful in forecasting earnings. |