The limited role of sustainability in mutual fund investor decisions: A machine learning approach

Despite the growth in the supply of socially responsible investment products, the weight of environmental, social and governance (ESG) factors in the decisions of mutual fund investors remains under-researched. We conducted a study relating fund flows to past returns, ESG performance and other financial variables using data from 3,767 US mutual funds from 2015 to 2021. First, we aimed to assess the importance of ESG performance in investment decisions. Next, we studied whether ESG performance is increasingly important or has reached its limit. Finally, we developed decisional models to predict the flows raised by each investment fund, its financial return and ESG performance. We used logistic regression, neural networks, random forest and gradient boosting decision trees. We found that the investors consider ESG performance, but the factors that matter most are past growth, mutual fund fees and past returns. Our models predicted the money raised by the funds, obtaining accuracy rates of around 70%. In addition to confirming that "past financial return does not guarantee future financial return," we found that "past ESG performance guarantees future ESG performance," which may be of interest to socially responsible investors.