Abstract
This white paper explores the construction of a reliable Environmental, Social, and Governance (ESG) scoring engine, with a focus on the importance of data sources and quality, selection of ESG indicators, weighting and aggregation methodologies, and the necessary validation and benchmarking procedures. The current challenges in ESG scoring and the importance of a robust ESG scoring system are addressed, citing its increasing relevance to stakeholders. Furthermore, different data types, namely self-reported data, third-party data, and alternative data, are critically evaluated for their respective merits and limitations. The paper further elucidates the complexities and implications involved in the choice of ESG indicators, illustrating the trade-offs between standardized and customized approaches. Various weighting methodologies including equal weighting, factor weighting, and multi-criteria decision analysis are dissected. The paper culminates in outlining processes for validating the ESG scoring engine, emphasizing the correlation with financial performance, and conducting robustness and sensitivity analyses. Practical examples through case studies exemplify the implementation of the discussed techniques. The white paper aims to provide insights and guidelines for practitioners, academics, and policy makers in designing and implementing robust ESG scoring systems.
Keywords:
Environmental; Social; and Governance (ESG); ESG Scoring Engine; ESG Indicator Selection; Weighting Methodologies; Validation.
Copyright: © 2023 Liu Y et al.
Grants and funding
This research is the result of the Innosuisse project no. 63513.1 INNO-ICT, Prototype for a reliable ESG Scoring engine - Green Finance and the authors gratefully acknowledge financial support from Innosuisse. The authors are grateful to working group members and management committee members of the COST (Cooperation in Science and Technology) Action CA19130 Fintech and Artificial Intelligence in Finance. This European network has been created in 2018 and now encompasses more than 280 researchers from 51 countries internationally. This document is based upon work from COST Action CA19130, supported by COST (European Cooperation in Science and Technology). COST (European Cooperation in Science and Technology) is a funding agency for research and innovation networks. Their Actions help connect research initiatives across Europe and enable scientists to grow their ideas by sharing them with their peers. This boosts their research, career, and innovation. The collaboration with the COST Action CA21163 Text functional and other high-dimensional data in econometrics: New models, methods, applications is acknowledged. Financial support by the Swiss National Science Foundation within the project Mathematics and Fintech - the next revolution in the digital transformation of the Finance industry (IZCNZ0-174853) is gratefully acknowledged. We are also grateful for financial support from the Swiss National Science Foundation under the grant IZSEZ0-211195 (Anomaly and Fraud Dection in Blockchain Networks). The authors also acknowledge financial support from the Swiss National Science Foundation within the project Narrative Digital Finance: a tale of structural breaks, bubbles \& market narratives (IZCOZ0-213370). We also acknowledge funding from the European Union's Horizon 2020 research and innovation program FIN-TECH: A Financial supervision and Technology compliance training programme under the grant agreement No 825215 (Topic: ICT-35-2018, Type of action: CSA). The Cooperation between ING Group and the University of Twente, in the context of promoting Artificial Intelligence in Finance in the Netherlands and beyond is gratefully acknowledged.