Open Access from Applied Stochastic Models in Business and Industry: Firms’ profitability and ESG score: A machine learning approach

Each week, we select a recently published Open Access article to feature. This week’s article comes from Applied Stochastic Models in Business and Industry   and investigates the relationship between the  ESG score and  firm’s profitability. 

The article’s abstract is given below, with the full article available to read here.

D’Amato, VD’Ecclesia, RLevantesi, SFirms’ profitability and ESG score: A machine learning approachAppl Stochastic Models Bus Ind20231– 19. doi: 10.1002/asmb.2758

Corporate social responsibility (CSR) is found to impact firms’ performance, for instance, enhancing reputation, increasing innovation capabilities, customer loyalty, and customer satisfaction help improve financial performance. However, the literature provides limited evidence of the relationship between CSR indicators, such as the ESG score, and the firm’s profitability, which is often measured by the earnings before interest and taxes (EBIT). We investigate this issue by analyzing a sample of about 400 companies constituting the EuroStoxx-600 index, from 2011 to 2020, using different machine learning models. The novelty of our contribution lies in assessing whether the ESG score has a significant influence on the firms’ profitability. Specifically, we investigate the relationship between ESG score and EBIT using machine learning interpretability toolboxes such as partial dependence plots and individual conditional expectation. Tools which help to measure the functional relationship between the predicted response and one or more features, while the Shapley value allows to examine the contribution of the feature to the prediction. Our findings show that the model can reach high levels of accuracy in detecting EBIT and that the ESG score is a promising predictor, compared to other traditional accounting variables.

More Details