Optimizing Portfolios With ESG, Dividends, and Volatility Factors via Machine Learning

Abstract

Factor investment is booming in global asset management, especially environmental, social, and governance (ESG), dividend yield, and volatility factors. In this chapter, we use data from the US securities market from 2003 to 2019 to predict dividends and volatility factors through machine learning and historical data–based methods. After that, we utilize particle swarm optimization to construct the Markowitz portfolio with limits on the number of assets and weight restrictions. The empirical results show that that the prediction ability using XGBoost is superior to the historical factor investment method. Moreover, the investment performance of our portfolio with ESG, high-yield, and low-volatility factors outperforms baseline methods, especially the S&P 500 ETF.

Citation

Chang, H.-H., Lai, C.-H., Lin, K.-L. and Lin, S.-K. (2024), "Optimizing Portfolios With ESG, Dividends, and Volatility Factors via Machine Learning", Lee, C.-F. and Yu, M.-T. (Ed.) Advances in Pacific Basin Business, Economics and Finance (Advances in Pacific Basin Business, Economics and Finance, Vol. 12), Emerald Publishing Limited, Leeds, pp. 193-214. https://doi.org/10.1108/S2514-465020240000012008