Design of ESG-compliant portfolios: a minimum divergence approach

Details

Supervisors

Vrins, Frédéric

Faculty

Louvain School of Management

Degree label

Master [120] : ingénieur de gestion, à finalité spécialisée

Abstract

In this master thesis, we will design ESG-compliant portfolios following two different strategies: (i) implement basic portfolios such as equally-weighted portfolios, Sharpe ratio portfolios and minimum-variance portfolios on a restricted universe considering ESG criteria; and (ii) implement minimum-divergence approach on portfolios with a good ESG score by targeting a Gaussian distribution with the two first moments of benchmark portfolios on an unrestricted universe. Thanks to the in-sample and out-of-sample analysis, we will compare three types of portfolios to each other: the benchmark portfolios, the ESG traditional ones and the minimum divergence portfolios. The goal of this master thesis is to see if it is possible while targeting the distribution of a certain portfolio on an unrestricted universe to improve the performance measures of an ESG-compliant portfolio. We concluded that in-sample it was generally possible for the minimum divergence portfolios to outperform the ESG traditional portfolios except for the Sharpe ratio strategy in terms of skewness, kurtosis and adjusted Sharpe ratio. For the out-of-sample performance, the results were poor for dataset with more assets because of the estimation errors and the results for the dataset with less assets were significant only with a small estimation window.