Do past ESG scores efficiently predict future ESG performance?

Given the effects of Environmental, Social, and Governance (ESG) scores on financial performance and stock returns, the prediction of future ESG scores is highly crucial. ESG scores are calculated using an enormous number of variables related to the sustainability practices of firms; thus, it is impractical for investors to come up with predictions of ESG performance. This paper aims to fill this gap by using only the past score-based and rating-based ESG performance as the determinant of future ESG performance using four machine learning-based algorithms; decision tree (DT), random-forest (RF), k-nearest neighbor (KNN), and logistic regression (LR). The proposed model is validated in BIST sustainability index companies. The results suggest that past ESG grade-based and numerical scores can be used as a determinant of future ESG performance. The results prove that a simple indicator could serve to predict future ESG scores rather than complex data alternatives. Using data from BIST sustainability index companies in Turkey, the findings demonstrate that past ESG grades and scores are reliable predictors of future ESG performance, offering a simple yet effective alternative to complex data-driven methods. This study not only contributes to advancing sustainable finance practices but also provides practical tools for emerging markets like Turkey to align corporate strategies with global sustainability standards. The methodological contributions also have broader relevance for international financial markets. [Display omitted] •This paper develops machine learning-based models to predict future ESG scores using only past score-based and rating-based ESG performance data.•Four machine learning algorithms are employed: decision tree (DT), random-forest (RF), k-nearest neighbor (KNN), and logistic regression (LR).•The findings demonstrate that past ESG grade-based and numerical scores can effectively predict future ESG performance.