The predictive power of ESG ratings in stock market returns

Abstract

Climate change is one of the greatest challenges humanity faces, driving the need for sustainable investment practices. Even though ESG investing has become popular with investors seeking to align their portfolios with sustainability goals, ESG information has yet to be included into modelling the stock market. With this thesis, I aim to study whether ESG ratings can predict stock market returns by complementing the Sum of the Parts model (Ferreira & Santa-Clara, 2011) with an ESG factor that I developed using two different approaches: cross-sectional and time-series. I find that ESG ratings enhance predictive models, with the Time-Series ESG factor demonstrating superior performance compared to the models without ESG integration. Variables, such as book-to-market ratio and dividend yield, benefited more from including an ESG factor, implying that ESG information can complement backward-looking metrics. However, the models did not yield significant improvements in risk-adjusted returns. Furthermore, robustness tests revealed different adaptability of the models to periods of higher market volatility. Overall, my results suggest that ESG ratings capture unique dimensions of stock returns’ performance that traditional macroeconomic indicators fail to account for, which shows the potential of integrating ESG considerations into investment strategies.

Date of Award	31 Jan 2025
Original language	English
Awarding Institution	Universidade Católica Portuguesa
Supervisor	Zoe Venter (Supervisor)