Predicting Stock Return Using Machine Learning
Keywords:
COVID-19, Neural Network, Machine Learning, Stock Return PredictionAbstract
This paper is to predicting stock return of equity securities in the Stock Exchange of Thailand by using machine learning with various factors. By predicting returns in 1-day, 1-month and 3-month returns and using 3 different machine learning algorithms are Artificial neural network (ANN) , Long Short-Term Memory (LSTM) and Random Forest (RF) to prove which algorithm can forecast a stock's return with the most accurate forecast. The results of the study demonstrated the ability to forecast stock returns using company data such as financial statements, financial ratio data, technical indicators, macroeconomic data. MacroEconomic, Exchange rate, Stock Index, Gold index and Historical Data. By using machine learning, the result is able to predict the returns of stocks as accurately as possible in order to determine the right investment strategy. This research has been shown that predicting stock returns in the short term using Machine Learning is not suitable for forecasting. But when forecasting stock returns over the long term, the Random Forest model can be used to make the most accurate predictions.
References
Baker, M. R., & Patil, R. B. (1998). Universal Approximation Theorem for Interval Neural Networks. Reliable Computing, 4, 235–239. doi:https://doi-org.ejournal.mahidol.ac.th/10.1023/A:1009951412412
Basak, S., Kar, S., Saha, S., Khaidem, L., & Dey, S. R. (2019). Predicting the direction of stock market prices using tree-based classifiers. North American Journal of Economics and Finance, 47(47), 552–567. doi:https://doi.org/10.1016/j.najef.2018.06.013
Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5-32. doi:https://doi.org/10.1023/A:
colah's blog. (2015). Understanding LSTM Networks. Retrieved from http://colah.github.io/posts/2015-08-Understanding-LSTMs/
Han, S. (2019). Stock Prediction with Random Forests and Long Short-term Memory. (Master Degree). Iowa State University,
Jiemwiriyakul, B., Sirianuntapiboon, P., & Lorsubkong, P. (2019). Portfolio Return Prediction using Neural Network. (Master degree Individual Study). Mahidol University
Jozefowicz, R., Zaremba, W., & Sutskever, I. (2015). An Empirical Exploration of Recurrent Network Architectures. Paper presented at the Proceedings of the 32nd International Conference on Machine Learning, Proceedings of Machine Learning Research. https://proceedings.mlr.press/v37/jozefowicz15.html
Kim, K.-j. (2003). Financial time series forecasting using support vector machines. Neurocomputing, 55(1), 307–319. doi:https://doi.org/10.1016/S0925-2312(03)00372-2
Loh, W. Y. (2011). Classification and regression trees. WIREs Data Mining and Knowledge Discovery, 1(1), 14-23. doi:https://doi.org/10.1002/widm.8
Ma, Y., Han, R., & Wang, W. (2021). Portfolio optimization with return prediction using deep learning and machine learning. Expert Systems with Applications, 165, 1-15. doi:https://doi.org/
1016/j.eswa.2020.113973
Nilson, M. (2019). A visual proof that neural nets can compute any function. Retrieved from http://neuralnetworksanddeeplearning.com/chap4.html
Patel, J., Shah, S., Thakkar, P., & Kotecha, K. (2015). Predicting stock market index using fusion of machine learning techniques. Expert Systems with Applications, 42(4), 2162-2172. doi:https://doi.org/10.1016/j.eswa.2014.10.031
Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2017). LSTM: A Search Space Odyssey. IEEE Transactions on Neural Networks and Learning Systems, 28(10), 2222-2232. doi:https://doi.org/10.1109/TNNLS.2016.2582924
