Presentation on YouTube

Deep learning methods, which can accommodate wide ranges of various stock characteristics to identify optimal investment portfolio or stochastic discount factor(SDF), have been criticized for extracting their superior performances from difficult to arbitrage stocks, high limits-to-arbitrage market conditions or extreme turnovers. 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.

Biography: Ruslan Goyenko is an Associate Professor of Finance at Desautels Faculty of Management, McGill University. He also held faculty appointments at the University of Toronto (Canada), Notre Dame University (USA) and is currently a visiting Associate Professor of Finance at Yale School of Management (USA). While his primary area of expertise is liquidity and liquidity risk among different asset classes, his most recent research is focused on the application of machine learning (ML)in asset pricing, such as return predictability, optimal portfolio construction, optimization, and risk management. He published in top finance peer-reviewed academic journals and co-organizes prestigious industry conferences on Applications of ML/AI in Asset Management. He is a recipient of numerous research grants from The Social Sciences and Humanities Research Council of Canada, and more recently from Autorité des Marchés Financiers (Financial Markets Regulatory Authority in Québec). In early 2021, Ruslan co-founded and is currently a scientific director of FIRM Labs (Financial Innovations and Risk Management Labs). FIRM is a research tank, which bridges the gap between two disciplines, financial economics and computer science. Its objective is to develop fundamental and practical applications of ML/AI in Asset Management, and finance in general.