A comparative study of portfolio optimization techniques in sustainable investing

Abstract

This Master's thesis navigates the intersection of machine learning (ML) and sustainable investing, specifically focusing on portfolio optimization. The study analyses conventional and ML-based methodologies, underlining the role and complications of incorporating ESG factors into the investment process. The research outlines the effectiveness of ML in ESG integration, offering a discussion on model selection tailored to investor-specific needs. The thesis also underlines the requirement for continuous adaptation in this rapidly changing field of sustainable investing. This work, serving as a guide for asset managers aiming to integrate sustainability principles effectively, is based on an extensive literature review.