My recent research is focused on applications of machine learning (ML) and AI in asset pricing.
We are quickly realizing that applying big data and AI/ML to such standard problems like asset allocation, optimal portfolio construction, risk management and investments overall provides significant incremental value compared to using traditional tools.
Yet off-shelf AI algorithms are not well suited for low signal-to-noise ratio of financial data. In my research, with my co-authors, we show how incorporating economic assumptions and restrictions into AI algorithms helps improving investment decision making processes.
with Nicolas Chapados (ServiceNow), Zhenzhen Fan(University of Manitoba), Issam Laradji (ServiceNow), Fred Liu (University of Guelph), and Chengyu Zhang (McGill)
It can. Using textual information from a complete history of regular quarterly and annual filings by U.S. corporations, we train classic machine learning algorithms and large language models, LLMs, to predict future earnings surprises. Only finance-objectives trained LLMs have the capacity to “understand” the contexts of previous 10-Q (10-K) releases to predict both positive and negative earnings surprises, and future firm returns.
Asset Pricing with Attention Guided Deep Learning
with Philippe Chatigny (University of Sherbrooke) and Chengyu Zhang (McGill)
The Joint Cross Section of Option and Stock Returns Predictability with Big Data and Machine Learning
with Chengyu Zhang (McGill)
Liquidity Guided Machine Learning: The Case of the Volatility Risk Premium
with Eric Ghysels (UNC) and Chengyu Zhang (McGill)
Volatility and the Cross-Section of Equity Returns: The Role of Short-Selling Constraints
with Paul Schultz (University of Notre Dame)