Search

Challenges and Opportunities in Stock Price Prediction: An Exploration Using an ANN-LSTM-Transformer Hybrid Model

Author(s)

Shengkai Ma

Affiliation(s)

Xi'an Jiaotong Liverpool University, China

Abstract

This paper explores the effectiveness of a hybrid model combining ANN, LSTM, and Transformer architectures for stock price prediction. The model integrates ANN for feature extraction, LSTM for capturing long-term dependencies, and Transformer for modeling complex relationships. However, its performance on real-world datasets fell short of traditional models like RF, SVM, and XGBoost, primarily due to insufficient hyperparameter tuning, inadequate data preprocessing, and the challenge of managing model complexity with limited training data. The findings emphasize the need for systematic optimization, advanced preprocessing techniques, and the inclusion of diverse data sources to improve predictive accuracy and robustness. While the current results highlight limitations, the hybrid model approach remains a promising avenue for tackling the complexities of stock prediction and enhancing financial decision-making.

Keywords

Stock Price Prediction; Artificial Neural Network (ANN); Long Short-Term Memory (LSTM); Transformer; Hybrid Model

References

[1] Meyler, A., Kenny, G., & Quinn, T. (1998). Forecasting Irish inflation using ARIMA models. [2] Ma, Q. (2020). Comparison of ARIMA, ANN and LSTM for stock price prediction. In E3S Web of Conferences (Vol. 218, p. 01026). EDP Sciences. [3] Tan, L., Liu, S., Gao, J., Liu, X., Chu, L., & Jiang, H. (2024). Enhanced self-checkout system for retail based on improved YOLOv10. Journal of Imaging, 10(10), 248. [4] Wolpert, D. H. (1992). Stacked generalization. Neural networks, 5(2), 241-259. [5] .Khashei, M., & Bijari, M. (2010). An artificial neural network (p, d, q) model for timeseries forecasting. Expert Systems with applications, 37(1), 479-489. [6] Yetis, Y., Kaplan, H., & Jamshidi, M. (2014, August). Stock market prediction by using artificial neural network. In 2014 world automation congress (WAC) (pp. 718-722). IEEE. [7] Gurjar, M., Naik, P., Mujumdar, G., & Vaidya, T. (2018). Stock market prediction using ANN. International Research Journal of Engineering and Technology, 5(3), 2758-2761. [8] Ghosh, A., Bose, S., Maji, G., Debnath, N., & Sen, S. (2019, September). Stock price prediction using LSTM on Indian share market. In Proceedings of 32nd international conference on (Vol. 63, pp. 101-110). [9] Pawar, K., Jalem, R. S., & Tiwari, V. (2019). Stock market price prediction using LSTM RNN. In Emerging Trends in Expert Applications and Security: Proceedings of ICETEAS 2018 (pp. 493-503). Springer Singapore. [10] Zhu, W., & Hu, T. (2021, July). Twitter Sentiment analysis of covid vaccines. In 2021 5th International Conference on Artificial Intelligence and Virtual Reality (AIVR) (pp. 118-122). [11] Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European journal of operational research, 270(2), 654-669. [12] `Xu, Y., Sushmit, A., Lyu, Q., Li, Y., Cao, X., Maltz, J. S., ... & Yu, H. (2022). Cardiac CT motion artifact grading via semi-automatic labeling and vessel tracking using synthetic image-augmented training data. Journal of X-Ray Science and Technology, 30(3), 433-445. [13] Kim, T., & Kim, H. Y. (2019). Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data. PloS one, 14(2), e0212320. [14] Choi, H. K. (2018). Stock price correlation coefficient prediction with ARIMA-LSTM hybrid model. arXiv preprint arXiv:1808.01560. [15] Vaswani, A. (2017). Attention is all you need. Advances in Neural Information Processing Systems.