Practical Applications of Weak Supervision and Black–Litterman for Automated ESG Portfolio Construction

Abstract

In Weak Supervision and Black–Litterman for Automated ESG Portfolio Construction, published in the Summer 2021 issue of The Journal of Financial Data Science, Alik Sokolov of SR.ai, and Kyle Caverly, Jonathan Mostovoy, Talal Fahoum, and Luis Seco of the University of Toronto’s RiskLab demonstrate the use of machine learning signals for ESG risk in portfolio optimization. The signals are created by a state-of-the-art natural language processing model applied to news articles from The New York Times. The authors demonstrate that the system achieves high accuracy across the ESG categories. They use the Black–Litterman model to combine the signals with a market-weight portfolio to find optimal portfolio weights that reflect the ESG risks. The resulting portfolio outperforms an otherwise equal non-ESG portfolio on a risk-adjusted basis. The approach is promising in that it avoids self-reported biases in the ESG data. Moreover, the results do not imply that risk-adjusted returns must be sacrificed in order to achieve ESG objectives. This area of research is particularly important as interest in ESG investing continues to grow.