Academic Journal of Computing & Information Science, 2021, 4(6); doi: 10.25236/AJCIS.2021.040603.
Zihe Tang1, Yanqi Cheng2, Ziyao Wang3
1Department of Mathematics, University of California, Los Angeles, California, United States
2Department of Economics, University of California, San Diego, California, United States
3Department of Corporate Finance, University of International Business and Economics, Beijing, China
These authors contributed equally to this work
Under frequent trading strategy, this paper assumes that rational investors will adopt a long-term conservative frequent trading strategy. By studying historical data by machine learning, we predict the future trend of stock prices and compare the returns of frequent trading strategy and long-term holding outcomes. The results show that the trend of stock prices is the key factor affecting quantitative investment strategy. This study enriches the relevant literature in the field of quantitative investment and focuses on the comparison of returns between frequent trading strategies and long-term holding strategies. It provides standards for selecting investment strategies in the securities market. In the practical sense, this paper proposes investment suggestions for investors to benefit from market fluctuations.
Quantitative Investment, Linear Regression Machine Learning Model, Long-Term Conservative Frequent Trading Strategy
Zihe Tang, Yanqi Cheng, Ziyao Wang. Quantified Investment Strategies and Excess Returns: Stock Price Forecasting Based on Machine Learning. Academic Journal of Computing & Information Science (2021), Vol. 4, Issue 6: 10-14. https://doi.org/10.25236/AJCIS.2021.040603.
[1] C. F. Camerer, “Prospect theory in the wild: Evidence from the field. Social Science Working Paper,” in California Institute of Technology, Pasadena, CA,1998.
[2] Y. Fang, J. Chen and Z. Xue, “Research on Quantitative Investment Strategies Based on Deep Learning,” in Algorithms,12(2),p.35, 2019.
[3] S. Gu, B. T. Kelly, and D. Xiu, “Empirical Asset Pricing via Machine Learning,” in SSRN Electronic Journal, 2018.
[4] J. Huang and J. Liu, “Using social media mining technology to improve stock price forecast accuracy,” in Journal of Forecasting, 39(1), pp.104–116, 2019.
[5] V. D. Ta, C. M. Liu and D. A. Tadesse, “Portfolio Optimization-Based Stock Prediction Using Long-Short Term Memory Network in Quantitative Trading,” in Applied Sciences, 10(2), p.437, 2020.
[6] J. Zhang, R. Shan and W. Su, “Applying Time Series Analysis Builds Stock Price Forecast Model,” in Modern Applied Science, 3(5), 2009.