Portfolios with return and volatility prediction for the energy stock market

Energy portfolios have important applications in many aspects of the energy market. This paper commonly integrates return and volatility prediction to advance portfolio models for the sake of building more efficient energy portfolios. In this regard, the extreme gradient boosting regression tree is applied to predict energy returns and volatilities, respectively. And six classical portfolio models are utilized to test the efficiency of this approach. Also, since these advanced portfolios own multiple objectives, this paper introduces prediction -based weights to transform these objectives. In addition, the component stocks of the CSI energy index are adopted for empirical tests. Empirical results show that commonly using return and volatility prediction to advance portfolio models significantly increases the performance of these models advanced only by return prediction. And prediction-based weights generally perform better than equal weights in transforming the multiple objectives of these advanced portfolios. Among these portfolios, the CVaR-F-PW portfolio performs the best. Robust tests show that 90% is the optimal confidence level for this portfolio. Therefore, the CVaR-F-PW portfolio is recommended for portfolio management in the energy stock market, and this portfolio is also useful to energy structure optimization, energy efficiency enhancement, and other applications in energy market.

Automated summary

This paper explores the use of return and volatility prediction to improve energy portfolio models, using extreme gradient boosting regression trees. Six classical portfolio models are tested, and the results show that using return and volatility prediction significantly enhances these models' performance. Prediction-based weights are also found to be more effective in transforming multiple objectives compared to equal weights. The CVaR-F-PW portfolio performs the best and is recommended for energy stock market portfolio management.