Social Sustainability in European Banks: A Machine Learning Approach using Interval- Based Composite Indicators
Carlo Drago (University of Niccolò Cusano); Loris Di Nallo (University of Cassino e del Lazio Meridionale); Maria Lucetta Russotto (University of Firenze)
G21, Q5, C02, C15, C43, C63
Social Index, Sustainable Banking, ESG, Monte-Carlo Simulation, Machine Learning, Interval-based Composite Indicators
Promoting social information reporting and disclosure can promote sustainable banking. The paper aims to measure banking social sustainability by constructing a new interval-based composite indicator using the Thomson Reuters database. In this work, we propose an approach to constructing interval-based composite indicators that enhance the composite indicator’s construction sensibly, allowing us to measure the uncertainty due to the choices in the composite indicator design. The methodological approach employed is based on a Monte-Carlo simulation and allows for improving the information the composite indicators can obtain. So, we measure the value of the social indicator and its subcomponents and the value’s uncertainty due to the different possible weights. The results show that the best international ESG practices in European banks relate to French and United Kingdom Banks, primarily than Italian banks. Finally, we analyze innovative perspectives and propose policy recommendations, considering the growing attention to the issue of ESG disclosure and its adherence to reality, to support sustainable banking ecosystems.
Citazione suggerita: C. Drago, L. Di Nallo, M. L. Russotto, ‘Social Sustainability in European Banks: A Machine Learning Approach using Interval-Based Composite Indicators’, Nota di Lavoro 013.2023, Milano, Italy: Fondazione Eni Enrico Mattei