Abstract
The need to predict stock price arises in the quantitative financial transaction field is a challenging problem. Long-short term memory (LSTM) neural network has shown a good effect on this problem. There are two main issues when implementing this method. One, it always suffers from huge attempts of constructing the neural network and adjustments of the hyper-parameter. Two, it often fails to find an excellent solution. We propose an AGA-LSTM algorithm, which uses an adaptive genetic algorithm to automatically optimize the network structure and hyper-parameters of the LSTM neural network. The simulation results show that the accuracy of the rise and fall of the stock outperforms LSTM as well as other previously machine learning models. Moreover, attempts are significantly less than other tuning methods.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Dattatray, P.G., Kumar, K.: Systematic analysis and review of stock market prediction techniques. Comput. Sci. Rev. 34 (2019)
Jin-Song, W.: An empirical study on the effectiveness of commonly used technical analysis methods in stock market. Southwestern University of Finance and Economics (2010)
Javad, Z., Mohammad, M.R.: Application of artificial neural network models and principal component analysis method in predicting stock prices on Tehran Stock Exchange. Physica A: Stat. Mech. Appl. 438 (2015)
Li-Ping, N., Zhi-Wei, N., Ya-Zhuo, G.: Stock trend prediction based on fractal feature selection and support vector machine. Expert Syst. Appl. 38(5), 5569–5576 (2011)
Su, Y., Yao-Yuan, S., Heng, S.: Time series prediction algorithm of stock market based on support vector machine. Sci. Technol. Eng. 02, 381–386 (2008)
Yakup, K., Melek, A.B., Ömer, K.B.: Predicting direction of stock price index movement using artificial neural networks and support vector machines: the sample of the Istanbul Stock Exchange. Expert Syst. Appl. 38(5), 5311–5319 (2011)
Christopher, K., Xuan, A.D., Nicolas, H.: Deep neural networks, gradient-boosted trees, random forests: statistical arbitrage on the S&P 500. Eur. J. Oper. Res. 259(2), 689–702 (2016)
Thomas, F., Christopher, K.: Deep learning with long short-term memory networks for financial market predictions. Eur. J. Oper. Res. 270(2), 654–669 (2018)
Pascanu, R., Gulcehre, C., Cho, K.: How to construct deep recurrent neural networks. In: International Conference on Learning Representations, pp. 1–13. IEEE Press, Piscataway (2014)
Dong, Y., Li, D.: Automatic Speech Recognition, vol. 237. Springer Verlag, London (2015)
Ma, X., Tao, Z., Wang, Y.: Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transp. Res. Part C: Emerg. Technol. 54, 187–197 (2015)
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: 2014 IEEE International Conference on Learning Representations. IEEE (2014)
Srivastava, N., Hinton, G., Krizhevsky, A.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Acknowledgement
This work was supported by the Key Project of Science and Technology Innovation 2030 funded by the Ministry of Science and Technology of China (No. 2018AAA0101301), the Key Projects of Artificial Intelligence of High School in Guangdong Province (No. 2019KZDZX1011) and The High School innovation Project (No. 2018KTSCX222).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
He, Y., Li, H., Wei, W. (2021). Application of LSTM Model Optimized Based on Adaptive Genetic Algorithm in Stock Forecasting. In: Tan, Y., Shi, Y., Zomaya, A., Yan, H., Cai, J. (eds) Data Mining and Big Data. DMBD 2021. Communications in Computer and Information Science, vol 1453. Springer, Singapore. https://doi.org/10.1007/978-981-16-7476-1_5
Download citation
DOI: https://doi.org/10.1007/978-981-16-7476-1_5
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7475-4
Online ISBN: 978-981-16-7476-1
eBook Packages: Computer ScienceComputer Science (R0)