Blog

I am not a professional blogger but a true passionate about finance research. As various projects are progressing, there is a lot of information which I find to be relevant not only to academics but also to professionals in the finance industry.

The purpose of this blog is to share this information in a concise way and make research knowledge more accessible, with the result of not necessarily using academic references, citations or specific vocabulary. The blog covers topics as varied as FinTech and its applications in finance to the outcomes of my various academic involvements. Enjoy the reading!

Blog

I am not a professional blogger but a true passionate about finance research. As various projects are progressing, there is a lot of information which I find to be relevant not only to academics but also to professionals in the finance industry.

The purpose of this blog is to share this information in a concise way and make research knowledge more accessible, with the result of not necessarily using academic references, citations or specific vocabulary. The blog covers topics as varied as FinTech and its applications in finance to the outcomes of my various academic involvements. Enjoy the reading!

Research Update

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.

Asset Pricing with Attention Guided Deep Learning

with Philippe Chatigny (University of Sherbrooke) and Chengyu Zhang (McGill)

Trading costs approach to portfolio construction strongly recommends considering multiple firm characteristics to reduce transaction and re-balancing expenses on the portfolio level. Deep learning methods, which can accommodate wide ranges of various stock characteristics to identify optimal and tradable stochastic discount factor (SDF) have been criticized for losing their superior performance after trading costs. We introduce attention-guided deep learning which, in a data driven way, allows identifying the most influential time-varying firm characteristics contributing to SDF. Attention dramatically improves SDF performance and reduces portfolio rebalancing costs. The attention guided SDF outperforms existing models after trading costs, excluding small and micro-cap stocks, avoids extreme portfolio weights, and unlike other models, exhibits the best performance during market regimes with the highest price efficiency.

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)

Demand Pressure and Option Returns

with Chengyu Zhang (McGill)