Sustainability and Genetic Algorithms: An Approach to Asset Portfolio Optimization

Purpose – This study aims to investigate the integration of climate change risk factors into asset portfolio optimization. Specifically, it seeks to evaluate the impact of maximizing sustainability on portfolio performance, and whether a balanced approach between profitability and sustainability can be achieved. Theoretical framework – The research is based on the Markowitz portfolio selection model combined with the principles of sustainable finance. A genetic algorithm is used to optimize asset allocation while incorporating sustainability metrics. Design/methodology/approach – A quantitative research method using a genetic optimization algorithm is employed to assess the effects of integrating a sustainability index into portfolio selection. The study compares traditional financial performance metrics with results incorporating climate change risk factors. Findings – The findings reveal that while maximizing sustainability may lead to short-term reductions in profitability, a balanced approach that integrates sustainability considerations can enhance long-term profitability. This balance enables investors to meet both financial goals and environmental responsibilities. Practical & social implications – The research contributes to the sustainable finance literature by offering insights into optimizing portfolios with ESG integration. Practically, it provides investors with strategies for aligning profitability and sustainability to promote economic growth while supporting environmental and social well-being. Future research could explore sector-specific implications and the different impacts of sustainability criteria. Originality/value – This study presents an innovative approach to asset portfolio optimization, advancing both the theoretical understanding of sustainable finance and providing practical tools for investors seeking to integrate climate change factors without compromising financial performance.