A self-learning and interpretable investment strategy based on extra-financial data
C. Geissler, V. Margot, Chaire DAMI, 2020.
Abstract: The investment industry has seen the importance of extra-financial criteria for companiesincrease very significantly in recent years. These extra-financial criteria, frequently referredto by the initials of the three pillars (E,S,G for Environment, Social and Governance) aim toquantify the positive or negative effects of a company’s activity in the human ecosystem. Thesedata are therefore of a different nature from the financial information included in balance sheetsand income statements. The multiplicity of these extra-financial data makes their integrationinto an investment process quite complex. The asset management industry already has standardstrategies such as sector exclusion or ’best in class’ selection strategies. These strategies aim toimprove the ESG scores of portfolios, without setting precise objectives on the creation of excessreturns. Here we present a self-learning and interpretable strategy that aims to simultaneouslyimprove extra-financial and possibly financial performance over the medium term.