Stock Returns Prediction with Moving Averages: Insights from VF Corporation Data

Zhexin Zhang

doi:10.54097/x11az659

Authors

Zhexin Zhang

DOI:

https://doi.org/10.54097/x11az659

Keywords:

Stock return prediction, machine learning, moving average.

Abstract

This study focusses on solving the problem of predicting the stock price in complex market. The traditional MAs have limits in capturing the percentage dynamic changes and non-linear features. By using VF Corp’s daily data from 2018 to 2023, this study turns the MAs into relative percentage change indicators. Three models (Linear Regression, Random Forest and Gradient Boosting) are tested which shows all these three models predicational power is limited. Linear Regression owns the least negative which is -0.0074, but its MSE (0.0003) is too low to believe. However, the Random Forest and Gradient Boosting have the problem of overfitting and their Test is -0.1140 and -0.1158. The mainly limitations are the reliance on the historical price and focusing on one stock price. As the accuracies of three models are bad, it reminds that in the future work, it should contain deep learning and more factors inputs to strengthen the accuracy.

Downloads

Download data is not yet available.

References

[1] Investopedia. Moving average (MA). Investopedia; 2025. Available from: https://www.investopedia.com/terms/m/movingaverage.asp

[2] Zuo Y, Kita E. Stock price forecast using Bayesian network. Expert Syst Appl. 2012;39(8):6729–37.

[3] Pai P-F, Lin C-S. A hybrid ARIMA and support vector machines model in stock price forecasting. Omega. 2005;33(6):497–505.

[4] Shahi TB, Shrestha A, Neupane A, Guo W. Stock price forecasting with deep learning: A comparative study. Mathematics. 2020;8(9):1441.

[5] Yahoo Finance. VF Corporation (VFC) Historical Data. Yahoo Finance; 2025. Available from: https://finance.yahoo.com/quote/VFC/history/

[6] Hunter JD. Matplotlib: A 2D graphics environment. Comput Sci Eng. 2007;9(3):90–5.

[7] Chen T, Guestrin C. XGBoost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016. p. 785–94.

[8] Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: Machine learning in Python. J Mach Learn Res. 2011;12(Oct):2825–30.

[9] Encyclopædia Britannica. Efficient market hypothesis (EMH). Encyclopædia Britannica; 2025. Available from: https://www.britannica.com/topic/efficient-market-hypothesis