EURO 2024 Copenhagen
Abstract Submission

EURO-Online login

3874. ESG factors driven asset management: a multi-layered approach for enhanced returns and risk mitigation

Invited abstract in session WB-6: Advancements of OR-analytics in statistics, machine learning and data science 17, stream Advancements of OR-analytics in statistics, machine learning and data science.

Wednesday, 10:30-12:00
Room: 1013 (building: 202)

Authors (first author is the speaker)

1. Salah AYARI
Université de Lille
2. Hayette Gatfaoui
Finance, IESEG School of Management

Abstract

Using machine learning, we implement a novel investing strategy that integrates environmental, social, and governance (ESG) factors, coupled with economic and risk considerations to enhance portfolio performance. The strategy involves a monthly screening of the stocks within the Russell 3000 index based on three filters. The first filter considers the economic cycle and uses leading indicators to identify future outperforming sectors. Then, using a clustering algorithm, the second filter ranks the sector-winning stocks by their ESG scores and selects the top-rated stocks from each ESG group. Finally, the remaining stocks are grouped via a clustering algorithm that focuses on risk metrics. Within each cluster, we select the stocks which exhibit the lowest loss potential as measured by the conditional value at risk (CVaR).

The resulting stock portfolio is constructed with the selected stocks and related asset allocation is achieved by using a convenient optimization method. The proposed investing strategy demonstrates the potential for achieving a desirable balance between risk, return, and ESG considerations. It proposes an active portfolio management architecture based on three layers, the main drivers being the sector rotation and ESG-factor investing policy.

Keywords

Status: accepted

Back to the list of papers