ESG-driven optimal portfolio selection for separated environmental, social, and governance preferences ESG-driven optimal

• Published in: Operational research Vol. 25; no. 2
• Main Author: Shushi, Tomer
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2025
• Subjects: Business and Management; Computational Intelligence; Management Science; Operations Research; Operations Research/Decision Theory; Original Paper; ESG scores; Mean-variance model; Optimal portfolio selection; Tail-value at risk; Risk measures
• ISSN: 1109-2858; 1866-1505
• DOI: 10.1007/s12351-025-00907-3

We propose and examine the optimal portfolio selection problem when the investor has different preferences in each of the portfolio’s environmental, social, and governance (ESG) average scores. We provide an explicit formula for the optimal weights in the case of the mean-variance model subject to the E, S, and G constraints and show that the same formula also holds in the case of other models that minimize a risk measure of the portfolio, with focusing on the tail-value-at-risk measure. We show that such models that go beyond the mean-variance model have the same formula for the optimal weight but with an effective risk aversion parameter that depends on the E, S, and G preferences of the investor, unlike in the original mean-variance model where the risk aversion is an external parameter. We then provide some numerical illustrations based on ten stocks from the NASDAQ, which offers clear guidance for allocating the portfolio between the different stocks and shows how each stock is sensitive to changes in the E, S, and G constraints.