Advances in Economics, Management and Political Sciences
- The Open Access Proceedings Series for Conferences
Series Vol. 60 , 05 January 2024
* Author to whom correspondence should be addressed.
Stock price prediction holds significant importance in the financial sector. It not only aids investors in making informed buy and sell decisions to achieve potential profits but also supports enterprises and financial institutions in risk assessment and management. This study utilized the stock prices of GM stocks spanning from 2013 to 2023 as dataset, with the goal of predicting their closing prices. This paper carefully identifies the parameters in the three model and one indicator of RMSE outcomes were computed. Visualizations of the results of the three model predictions are also provided. After comparing the indicator of the three models, it is found that the RMSE for LSTM is the smallest, indicating that the LSTM outperforms the KNN and linear regression from the perspective of forecast accuracy. The research highlights the application of the machine learning algorithm of LSTM in the prediction of the prices of financial assets and its practical value in financial market analysis.
LSTM, KNN, linear regression
1. Orsato, R. J., & Wells, P. (2007). The automobile industry & sustainability. Journal of cleaner production, 15(11-12), 989-993.
2. Peng, Z. Y. (2004). Non-linear characteristics and prediction models of Shanghai and Shenzhen stock markets (Doctoral dissertation, Wuhan University of Technology).
3. Hu, P. (2014). Stock prediction model based on ANN method (Doctoral dissertation, Chongqing University).
4. Li, L. (2015). A comparative study on stock price prediction ability based on GARCH and BP-ANN (Doctoral dissertation, Southwest Jiaotong University).
5. Zhou, B. (2009). A study on stock price index prediction based on GA's ANN (Doctoral dissertation, Wuhan University of Technology).
6. Tao, Y. Y. (Year). Application of decision tree and neural network algorithms in stock classification prediction (Doctoral dissertation, Hangzhou Dianzi University).
7. Wang, Y., Chen, D., & Tang, Y. (2019). Stock prediction based on CART decision tree and boosting methods. Journal of Harbin University of Science and Technology, 24(6), 6.
8. Meng, X., & Liu, X. (1997). Stock market modeling and prediction based on fuzzy neural networks and genetic algorithms. Information and Control, 26(5), 5.
9. Lu, Q., Ye, D., & Nan, M. (2010). Stock price prediction based on genetic algorithms and neural networks. Computer Development and Applications, 23(2), 2.
10. Chen, Y. (Year). Research on stock prediction models (Doctoral dissertation, Harbin Engineering University).
11. Imandoust, S. B., & Bolandraftar, M. (2013). Application of k-nearest neighbor (knn) approach for predicting economic events: Theoretical background. International journal of engineering research and applications, 3(5), 605-610.
12. Svozil, D., Kvasnicka, V., & Pospichal, J. (1997). Introduction to multi-layer feed-forward neural networks. Chemometrics and intelligent laboratory systems, 39(1), 43-62.
13. Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2016). LSTM: A search space odyssey. IEEE transactions on neural networks and learning systems, 28(10), 2222-2232.
14. Lipton, Z. C., Kale, D. C., Elkan, C., & Wetzel, R. (2015). Learning to diagnose with LSTM recurrent neural networks. arXiv preprint arXiv:1511.03677.
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. Authors who publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open Access Instruction).