Investment Portfolio Optimization and ESG Factors Impact on Financial Performance using Machine Learning

Sharma, Akansha (2024) Investment Portfolio Optimization and ESG Factors Impact on Financial Performance using Machine Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration Manual) Download (562kB) | Preview

Abstract

This study aims to examine the effects of incorporating ESG factors in the investment portfolio and improving the performance of the portfolio using machine learning. The rationale for the study arises from the increasing relevance of sustainable investment and the challenges of integrating ESG factors into investment decision-making to increase returns and manage risks profitably. By applying deep learning technologies, such as LSTM and SVM, the paper contrasts the efficiency of ESG portfolios with standard ones. The study explores that comparable financial results can be achieved while aiding sustainability goals with ESG-integrated portfolios. The integration of ESG factors in the portfolio showed a Sharpe ratio of 0.538 and balanced performance metrics, close to the Sharpe ratio (0.541) of the non-ESG portfolio. Portfolios optimized for specific ESG components, such as Environmental Risk (Sharpe Ratio: 0.505; ESG Score: 0.841) provided a better fit to sustainability criteria while slightly lower financial parameters. Therefore, these results demonstrate the effectiveness of ESG factors in improving investment approaches and providing optimized results regarding the Sharpe ratio, volatility, and maximum drawdown. Consequently, it becomes possible to tap into the potential of machine learning in expanding the ESG portfolio while delivering significant improvements in ethically and financially attainable results. Hence, for the creation of comprehensive, efficient, responsible, and sustainable investment practices, this research contributes to ESG integration frameworks. Future work may expand on these results by exploring broader data sets and more complex techniques to define portfolio optimization.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Clifford, William UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HG Finance > Investment Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	05 Sep 2025 08:49
Last Modified:	05 Sep 2025 08:49
URI:	https://norma.ncirl.ie/id/eprint/8807

Actions (login required)

View Item