Download pdf
A Multi-Task Learning Model for Stock Market Forecasting
- 1 Department of Statistics and Data Science, National University of Singapore, Singapore
* Author to whom correspondence should be addressed.
Abstract
Time series analysis plays a pivotal role in diverse domains, facilitating critical tasks such as forecasting, classification, and anomaly detection. This paper introduces a multi-task learning (MTL) model utilizing a deep learning framework to simultaneously predict three key financial indicators: trading volume, closing price, and volatility. By leveraging shared representations across tasks, the MTL model captures intricate dependencies and enhances generalization, outperforming single-task benchmark models—ARIMA and univariate Deep Learning (DL). The MTL model achieves over 50% reduction in MAE and RMSE compared to ARIMA and approximately 10% improvement over DL. The results demonstrate the ability of MTL to exploit inter-task relationships, delivering more accurate and robust forecasting for stock markets. This work highlights the potential of multi-task learning framework in enhancing financial time series forecasting.
Keywords
Multi-task Learning, Deep learning, Financial Forecasting, Time Series Analysis
[1]. Sen, J., & Chaudhuri, T. D. (2017, April 25). A time series Analysis-Based Forecasting Framework for the Indian Healthcare sector. arXiv.org. https://arxiv.org/abs/1705.01144
[2]. Helli, S. S., Tanberk, S., & Demir, O. (2022). Forecasting Energy Consumption Using Deep Learning in Smart Cities. IEEE, 1–6. https://doi.org/10.1109/icaiot57170.2022.10121846
[3]. Hoseinzade, E., & Haratizadeh, S. (2019). CNNpred: CNN-based stock market prediction using a diverse set of variables. Expert Systems With Applications, 129, 273–285. https://doi.org/10.1016/j.eswa.2019.03.029
[4]. Mondal, P., Shit, L., & Goswami, S. (2014). Study of Effectiveness of Time Series Modeling (ARIMA) in forecasting stock Prices. International Journal of Computer Science Engineering and Applications, 4(2), 13–29. https://doi.org/10.5121/ijcsea.2014.4202
[5]. Petrică, A., Stancu, S., & Tindeche, A. (2016). Limitation of ARIMA models in financial and monetary economics. DOAJ (DOAJ: Directory of Open Access Journals). https://doaj.org/article/3b26dede3d584d9f8d3e52e0d0c5ae6e
[6]. Vasudevan, R. D., & Vetrivel, S. C. (2016). Forecasting Stock Market Volatility using GARCH Models: Evidence from the Indian Stock Market. Asian Journal of Research in Social Sciences and Humanities, 6(8), 1565. https://doi.org/10.5958/2249-7315.2016.00694.8
[7]. Siami-Namini, S., Tavakoli, N., & Namin, A. S. (2019, November 21). A comparative analysis of forecasting financial time series using ARIMA, LSTM, and BILSTM. arXiv.org. http://arxiv.org/abs/1911.09512
[8]. Büyükşahin, Ü. Ç., & Ertekin, Ş. (2019). Improving forecasting accuracy of time series data using a new ARIMA-ANN hybrid method and empirical mode decomposition. Neurocomputing, 361, 151–163. https://doi.org/10.1016/j.neucom.2019.05.099
[9]. Mei, W., Xu, P., Liu, R., Liu, J., & School of Management Science and Engineering Nanjing University of Finance and Economics. (2018). Stock price prediction based on ARIMA - SVM model. In 2018 International Conference on Big Data and Artificial Intelligence (ICBDAI 2018) [Conference-proceeding]. Francis Academic Press. https://doi.org/10.25236/icbdai.2018.00849
[10]. Ranjan, R., Patel, V. M., & Chellappa, R. (2017). HyperFace: a deep Multi-Task learning framework for face detection, landmark localization, pose estimation, and gender recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(1), 121–135. https://doi.org/10.1109/tpami.2017.2781233
[11]. Samala, R. K., Chan, H., Hadjiiski, L. M., Helvie, M. A., Richter, C., & Cha, K. H. (2018). Cross-domain and multi-task transfer learning of deep convolutional neural network for breast cancer diagnosis in digital breast tomosynthesis. Medical Imaging 2018: Computer-Aided Diagnosis, 25. https://doi.org/10.1117/12.2293412
[12]. Ma, T., & Tan, Y. (2020). Multiple Stock Time Series Jointly Forecasting with Multi-Task Learning. 2022 International Joint Conference on Neural Networks (IJCNN), 1–8. https://doi.org/10.1109/ijcnn48605.2020.9207543
[13]. Yuan, C., Ma, X., Wang, H., Zhang, C., & Li, X. (2023). COVID19-MLSF: A multi-task learning-based stock market forecasting framework during the COVID-19 pandemic. Expert Systems With Applications, 217, 119549. https://doi.org/10.1016/j.eswa.2023.119549
[14]. Geurts, M., Box, G. E. P., & Jenkins, G. M. (2015). Time Series Analysis: Forecasting and Control (5th Ed.) https://doi.org/10.2307/3150485
[15]. Hyndman, R. J., & Athanasopoulos, G. (2013). Forecasting: principles and practice.
[16]. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
[17]. Dive into Deep Learning — Dive into Deep Learning 1.0.3 documentation. (n.d.). https://d2l.ai/
[18]. Gers, F. A., Schmidhuber, J., & Cummins, F. (2000). Learning to Forget: Continual Prediction with LSTM. Neural Computation, 12(10), 2451–2471. https://doi.org/10.1162/089976600300015015
[19]. Zhang, Y., & Yang, Q. (2017). An overview of multi-task learning. National Science Review, 5(1), 30–43. https://doi.org/10.1093/nsr/nwx105
[20]. Ruder, S. (2017, June 15). An overview of Multi-Task learning in deep neural networks. arXiv.org. https://arxiv.org/abs/1706.05098
Cite this article
Jiang,X. (2025). A Multi-Task Learning Model for Stock Market Forecasting. Applied and Computational Engineering,146,1-8.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Volume title: Proceedings of SEML 2025 Symposium: Machine Learning Theory and Applications
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) 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 policy for details).