ESG Score Prediction Using Machine Learning, Gap Analysis

This study aims to identify the main research gaps in Environmental, Social, and Governance (ESG) score prediction using Machine Learning (ML). To achieve this, a qualitative approach is adopted based on a Systematic Literature Review (SLR) using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, alongside gap analysis employing the seven research gaps model developed by Miles. Considering the detailed gap analysis conducted above, several research problems can be derived from the identified practical knowledge, empirical, and population research gaps for further analysis and future studies: the lack of proper input features, the absence of novel ML models, the lack of diverse datasets testing, inadequate market diversity in testing, and a lack of recent years testing. This study not only contributes to the body of knowledge by finding the main gaps identified in recent studies but also has the potential to inspire researchers to address these gaps and potentially revolutionize the field, thereby fostering innovation and advancement in ESG score prediction using ML. By addressing these gaps, researchers can significantly enhance the accuracy and reliability of ESG score prediction models, leading to more informed decision-making in the field.