Investment Performance of Machine Learning: Analysis of S&P 500 Index

• Main Authors: Chia-Cheng Chen, Chun-Hung Chen, Ting-Yin Liu
• Format: Article
• Language: English
• Published: EconJournals 2019-12-01
• Series: International Journal of Economics and Financial Issues
• Online Access: http://www.econjournals.com/index.php/ijefi/article/view/8925

<p>This study aims to explore the prediction of S&amp;P 500 stock price movement and conduct an analysis of its investment performance. Based on the S&amp;P 500 index, the study compares three machine learning models: ANN, SVM, and Random Forest. With a performance evaluation of S&amp;P 500 index historical data spanning from 2014 to 2018, we find: (1) By overall performance measures, machine learning models outperform benchmark market index. (2) By risk-adjusted measures, the empirical results suggest that Random Forest generates the best performance, followed by SVM and ANN.</p><p><strong>Keywords: </strong>ANN, SVM, Random Forest, Machine Learning, Investment Performance</p><p><strong>JEL Classifications: </strong>C11; C15; C53; G17</p><p>DOI: <a href="https://doi.org/10.32479/ijefi.8925">https://doi.org/10.32479/ijefi.8925</a></p>