Stock Market Analysis and Prediction Using LSTM

Authors

  • Yuhui Chen

DOI:

https://doi.org/10.54691/bcpbm.v36i.3489

Keywords:

Long short-term memory (LSTM), Prediction, Stock Prices, Recurrent neural network (RNN)

Abstract

Even for professionals and analysts, predicting the value of stocks has proved to be a challenging endeavor. Because they shed light on the expected future path of the stock market, accurate prediction systems for the stock market are beneficial to traders, investors, and analysts. This is because traders, investors, and analysts can better anticipate the market's behavior. The increase in available choices for financial investments has contributed to the complexity and unpredictability of the stock market. The goal of this project is to develop a model that could precisely depicting the market’s complexity as well as its high degree of volatility. The long short-term memory (LSTM) architecture of a neural network was implemented in this study to estimate Apple's next day closing price throughout the preceding decade. To forecast how the stock market will behave, its six fundamental indicators are integrated in a logical and well-balanced way. These indicators account for fundamental market data, macroeconomic data, and technical indications.

Downloads

Download data is not yet available.

References

H. Jia, "Investigation into the efficacy of long short term memory networks for stock price forecasting," arXiv preprint arXiv:1603.07893, 2016.

S.HochreiterandJ.Schmidhuber. Longshort-termmemory. Neural computation, 9:1735–80, 12 1997.

C. Olah. http://colah.github.io/posts/2015-08-Understanding-LSTMs/.

H. Goel, I. Melnyk, and A. Banerjee. arXiv preprint, 2017. R2N2: Residual recurrent neural networks for multivariate time series forecasting. Available at https://arxiv.org/abs/1709.03159".

G. Petnehazi. arXiv preprint, 2019: Recurrent neural networks for time series forecasting. Available at https://arxiv.org/pdf/1901.00069.pdf.

J. Roman and A. Jameel, "Backpropagation and recurrent neural nets in financial analysis of multiple stock market returns," in System Sciences, 1996., Proceedings of the Twenty-Ninth Hawaii International Conference on, vol. 2, IEEE, 1996, pp. 346-378.

E. W. Saad, D. V. Prokhorov, and D. C. Wunsch, "Comparative study of stock trend prediction using time delay, recurrent, and probabilistic neural networks," IEEE Transactions on neural networks, vol. 9, no. 6, 1998, pp. 1456–1458.

M.-C. Chan, C.-C. Wong, and C.-C. Lam, "Financial time series forecasting by neural network using conjugate gradient learning method and multiple linear regression weight initialization," Computing in Economics and Finance, vol. 61, 2000.

G. E. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time series analysis: predicting and control. 2015, John Wiley & Sons

Stock Price Trend Prediction Using Supervised Learning Methods by Sharvil Katariya and Saurabh Jain.

Nelson et al., 2017, Stock market price movement prediction using LSTM neural networks, 2017 international joint conference on neural networks (IJCNN), IEEE (2017),

Downloads

Published

2023-01-13

How to Cite

Chen, Y. (2023). Stock Market Analysis and Prediction Using LSTM. BCP Business & Management, 36, 381–386. https://doi.org/10.54691/bcpbm.v36i.3489