| Institution: | 1. Centre for Research on Economic Relations, and The Royal Melbourne Institute of Technology, University of Gävle, Gävle, Sweden;2. University of Gävle, Gävle, Sweden;3. Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden;4. Department of Economics, Geography, Law and Tourism, Centre for Research on Economic Relations, Mid Sweden University, Sundsvall, Sweden;5. West Virginia University, Morgantown, West Virginia, USA;6. The Royal Melbourne Institute of Technology, School of Accounting, Information Systems & Supply Chain, RMIT University, Melbourne, VIC, Australia;7. Department of Accounting and Logistics, School of Business and Economics, Linnaeus University, Växjö, Sweden;8. Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden
International Institute for Applied Systems Analysis (IIASA), Laxenburg, Austria |
| Abstract: | We use machine learning with a cross-sectional research design to predict governance controversies and to develop a measure of the governance component of the environmental, social, governance (ESG) metrics. Based on comprehensive governance data from 2,517 companies over a period of 10 years and investigating nine machine-learning algorithms, we find that governance controversies can be predicted with high predictive performance. Our proposed governance rating methodology has two unique advantages compared with traditional ESG ratings: it rates companies' compliance with governance responsibilities and it has predictive validity. Our study demonstrates a solution to what is likely the greatest challenge for the finance industry today: how to assess a company's sustainability with validity and accuracy. Prior to this study, the ESG rating industry and the literature have not provided evidence that widely adopted governance ratings are valid. This study describes the only methodology for developing governance performance ratings based on companies' compliance with governance responsibilities and for which there is evidence of predictive validity. |
