The week's pick
Random Articles
Reseach Article
Enhancing Stock Market Forecasting using Transformer-based Models
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 6 |
| Year of Publication: 2025 |
| Authors: Samarth Agarwal, Syed Wajahat Abbas Rizvi |
10.5120/ijca2025924892
|
Samarth Agarwal, Syed Wajahat Abbas Rizvi . Enhancing Stock Market Forecasting using Transformer-based Models. International Journal of Computer Applications. 187, 6 ( May 2025), 20-25. DOI=10.5120/ijca2025924892
Abstract
Recent advances in artificial intelligence, particularly in natural language processing (NLP), have been driven by the development of transformer-based architectures. These models, such as BERT, GPT, and their derivatives, have shown unprecedented capabilities in understanding and generating text due to their ability in capturing long range contextuality. In the financial domain, especially in the stock market, transformers hold immense potential. This paper explores how transformer models can revolutionize stock market analysis, focusing on applications in sentiment analysis, event detection, and predictive modelling. Furthermore, this paperdiscusses challenges such as data scarcity, domain adaptation, interpretability and the ethical implications of deploying such systems in high-stakes environments. This paper depicts the future use of Transformers in various sectors such as finance and trading, investing, reviews apart from traditional text generation and chatbot use.
References
- Shmilovici, A.: Support vector machines for financial time series. In: Stock Market Modeling and Forecasting, 47–79 (2009).
- Nelson, D.M., Pereira, A.C., & de Oliveira, R.A.: Stock market’s price movement prediction with LSTM neural networks. IEEE International Joint Conference on Neural Networks (IJCNN), 1419–1426 (2017).
- Atsalakis, G.S., & Valavanis, K.P.: Surveying stock market forecasting techniques – Part II: Soft computing methods. Expert Systems with Applications 36(3), 5932–5941 (2009)
- Hawkins, D.M.: The problem of overfitting. Journal of Chemical Information and Computer Sciences 44(1), 1–12 (2004).
- Cont, R.: Empirical properties of asset returns: stylized facts and statistical issues. Quantitative Finance 1(2), 223–236 (2001).
- Zhang, G., Eddy Patuwo, B., & Hu, M.Y.: Forecasting with artificial neural networks: The state of the art. International Journal of Forecasting 14(1), 35–62 (1998).
- Makridakis, S., Spiliotis, E., &Assimakopoulos, V.: Statistical and machine learning forecasting methods: Concerns and ways forward. PLoS ONE 13(3), e0194889 (2018).
- Feng, G., Polson, N., & Xu, J.: Deep learning for predicting asset returns. The Journal of Financial Econometrics 18(2), 282–306 (2020).
- Pearl, J.: Causal inference in statistics: An overview. Statistics Surveys 3, 96–146 (2009).
- Doshi-Velez, F., & Kim, B.: Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608 (2017).
- Lo, A.W.: Adaptive markets hypothesis: Market efficiency from an evolutionary perspective. The Journal of Portfolio Management 30(5), 15–29 (2004).
- Fama, E.F.: Efficient capital markets: A review of theory and empirical work. Journal of Finance 25(2), 383–417 (1970).
- Guyon, I., &Elisseeff, A.: An introduction to variable and feature selection. Journal of Machine Learning Research 3, 1157–1182 (2003).
- Sze, V., Chen, Y.H., Yang, T.J., & Emer, J.S.: Efficient processing of deep neural networks: A tutorial and survey. Proceedings of the IEEE 105(12), 2295–2329 (2017).
- Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., &Polosukhin, I.: Attention is all you need. Advances in Neural Information Processing Systems (NeurIPS), 5998–6008 (2017).
- Lim, B., Arik, S.O., Loeff, N., & Pfister, T.: Temporal fusion transformers for interpretable multi-horizon time series forecasting. Advances in Neural Information Processing Systems (NeurIPS), 33, 6454–6466 (2021).
- Li, S., Jin, X., Xuan, Y., Zhou, X., Chen, W., Wang, Y., & Yan, X.: Enhancing the locality and breaking the memory bottleneck of Transformer on time series forecasting. Advances in Neural Information Processing Systems (NeurIPS), 32, 5243–5253 (2019).
- Wu, H., Xu, J., Wang, J., & Long, M.: Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Advances in Neural Information Processing Systems (NeurIPS), 34, 22419–22430 (2021).
- Cini, A., Alaa, A., & van der Schaar, M.: Filling the gaps: Multivariate time series imputation by learning from similar sequences. Proceedings of the AAAI Conference on Artificial Intelligence, 35(12), 9277–9286 (2021).
- Zeng, A., Zhang, Z., Gou, Y., Bengio, Y., & Zhang, J.: Are transformers effective for time series forecasting? Advances in Neural Information Processing Systems (NeurIPS), 34, 27756–27768 (2022).
- Salinas, D., Flunkert, V., Gasthaus, J., &Januschowski, T.: DeepAR: Probabilistic forecasting with autoregressive recurrent networks. International Journal of Forecasting, 36(3), 1181–1191 (2020).
- Lundberg, S.M., & Lee, S.I.: A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems (NeurIPS), 30, 4765–4774 (2017).
- Jain, S., & Wallace, B.C.: Attention is not explanation. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 3543–3556 (2019).
Index Terms
Keywords