ESG investments: Filtering versus machine learning approaches

Speaker: Dr. Carmine de Franco, Head of Research & ESG, Ossiam

Abstract: We designed a machine learning algorithm that identifies patterns between ESG profiles and financial performances for companies in a large investment universe. The algorithm consists of regularly updated sets of rules that map regions into the high-dimensional space of ESG features to excess return predictions. The final aggregated predictions are transformed into scores which allow us to design simple strategies that screen the investment universe for stocks with positive scores. By linking the ESG features with financial performances in a non-linear way, our strategy based upon our machine learning algorithm turns out to be an efficient stock picking tool, which outperforms classic strategies that screen stocks according to their ESG ratings, as the popular best-in-class approach. Our paper brings new ideas in the growing field of financial literature that investigates the links between ESG behavior and the economy. We show indeed that there is clearly some form of alpha in the ESG profile of a company, but that this alpha can be accessed only with powerful, non-linear techniques such as machine learning.

Bio: Carmine de Franco is the head of research at Ossiam, an asset management firm specializing in systematic and quantitative ETFs, located in Paris. Graduated in Mathematics from the University of Roma II – Tor Vergata and the University Paris VII – Denis Diderot, he holds a PhD in Probability and a master’s degree in Financial Random Modelling from the University Paris VII-Denis. Carmine joined Ossiam in May 2012 after working for 4 years at the Faculty of Mathematics of the University of Paris VII (Université Denis Diderot). His domain of expertise spans from mathematics and probability theory to statistics, from financial research to the design of investment strategy and cross-assets portfolio construction. More recently, his research topics have focused on ESG themes, low carbon approaches and biodiversity in financial investments, machine learning and artificial intelligence. He is co-author of several research papers on portfolio insurance, modelling and hedging with stochastic jumps, regime switching models, interest rates, equity, smart beta and factor investing, ESG, machine learning, Bayesian learning and portfolio construction under uncertainty, carbon and biodiversity.

Ossiam: is a Paris-based asset manager focused on quantitative and systematic investment solutions since 2009 with a distinct vision: providing clear, transparent access to quantitative, research-based strategies. Ossiam is an affiliate of Natixis Investment Managers and manages a range of ETFs, open ended-funds, dedicated funds and mandates across a variety of asset classes and themes. Ossiam is a signatory of the UN-supported Principles for Responsible Investment since 2016 and a signatory of the Finance for Biodiversity Pledge since 2021. As of end of July 2021, Ossiam had 5 bn EUR in assets under management.