Predictive and prescriptive analytics for ESG performance evaluation: A case of Fortune 500 companies

Given the growing importance of organizations' environmental, social, and governance (ESG) performance, studies employing AI-based techniques to generate insights from ESG data for investors and managers are limited. To bridge this gap, this study proposes an AI-based multi-stage ESG performance prediction system consolidating clustering for identifying patterns within ESG data, association rule mining for uncovering meaningful relationships, deep learning for predictive accuracy, and prescriptive analytics for actionable insights. This study is grounded in the big data analytics capability view that has emerged from the dynamic capabilities theory. The model is validated using an ESG dataset of 470 Fortune listed 500 companies obtained from the Refinitiv database. The model offers practical guidance for decision-makers to maintain or enhance their ESG scores, crucial in a business landscape where ESG metrics significantly affect investor choices and public image.