A Study On Stock Price Prediction Using Bi-Directional LSTM
Keywords:
Stock Price Prediction, Bi-Directional LSTM, Stock Exchange, Deep Learning.Abstract
This study analyzed a deep learning strategy based on "Bi- Directional LSTM network" for forecasting stock values. The suggested method takes in past stock prices and outputs hypothetical new stock values. Utilizing 30-day window width for prediction, the model got trained and tested on the "New York Stock Exchange", the Nikkei 225, and the Nasdaq Composite. The suggested method indicated a MAPE for the NYSE of 0.014, for the Nikkei 225 of 0.01, and for the Nasdaq Composite of 0.018. These results were compared with the results of a base paper, which showed significant improvement in terms of prediction accuracy. Future work includes testing the studied approach on other stock exchanges and exploring the use of additional features such as news sentiment analysis for further improvements. Overall, this approach showed promise in the field of stock price prediction and could potentially benefit investors and financial analysts in making informed decisions.
References
[1] Cai, Yongming, et al. "Financial time series forecasting using directed-weighted chunking SVMs." Mathematical Problems in Engineering 2014 (2014). https://doi.org/10.1155/2014/170424
[2] Eapen, Jithin, Doina Bein, and Abhishek Verma. "Novel deep learning model with CNN and bi-directional LSTM for improved stock market index prediction." 2019 IEEE 9th annual computing and communication workshop and conference (CCWC). IEEE, 2019. https://doi.org/10.1109/CCWC.2019.8666592
[3] Li, Yuhong, and Weihua Ma. "Applications of artificial neural networks in financial economics: a survey." 2010 International symposium on computational intelligence and design. Vol. 1. IEEE, 2010. https://doi.org/10.1109/ISCID.2010.70
[4] Abe, Masaya, and Kei Nakagawa. "Cross-sectional stock price prediction using deep learning for actual investment management." Proceedings of the 2020 Asia Service Sciences and Software Engineering Conference. 2020 https://doi.org/10.1145/3399871.3399889
[5] Idrees, Sheikh Mohammad, M. Afshar Alam, and Parul Agarwal. "A prediction approach for stock market volatility based on time series data." IEEE Access 7 (2019): 17287-17298. https://doi.org/10.1109/ACCESS.2019.2895252
[6] Houssein, Essam H., et al. "An efficient equilibrium optimizer with support vector regression for stock market prediction." Neural Computing and Applications (2022): 1-36.
[7] Chhajer, Parshv, Manan Shah, and Ameya Kshirsagar. "The applications of artificial neural networks, support vector machines, and long-short term memory for stock market prediction." Decision Analytics Journal 2 (2022): 100015. https://doi.org/10.1016/j.dajour.2021.100015
[8] Meesad, Phayung, and Risul Islam Rasel. "Predicting stock market price using support vector regression." 2013 International Conference on Informatics, Electronics and Vision (ICIEV). IEEE, 2013. https://doi.org/10.1109/ICIEV.2013.6572570
[9] Guresen, Erkam, Gulgun Kayakutlu, and Tugrul U. Daim. "Using artificial neural network models in stock market index prediction." Expert Systems with Applications 38.8 (2011): 10389-10397. https://doi.org/10.1016/j.eswa.2011.02.068
[10] Hermans, Michiel, and Benjamin Schrauwen. "Training and analysing deep recurrent neural networks." Advances in neural information processing systems 26 (2013).
[11] Bao, Wei, Jun Yue, and Yulei Rao. "A deep learning framework for financial time series using stacked autoencoders and long-short term memory." PloS one 12.7 (2017): e0180944. https://doi.org/10.1371/journal.pone.0180944
[12] Ghahramani, Mohammadmahdi, and Hamid Esmaeili Najafabadi. "Compatible deep neural network framework with financial time series data, including data preprocessor, neural network model and trading strategy." arXiv preprint arXiv:2205.08382 (2022).
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Abhay Rohit , Akash Verma, Pranjal Khare
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Re-users must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. This license allows for redistribution, commercial and non-commercial, as long as the original work is properly credited.
7
