Predicting Index Trend Using Hybrid Neural Networks with a Focus on Multi-Scale Temporal Feature Extraction in the Tehran Stock Exchange

Document Type : Research Paper

Authors

1 Assistant Prof., Department of Financial Management and Insurance, Faculty of Management and Accounting, Shahid Beheshti University, Tehran, Iran.

2 MSc., Department of Financial Management, Faculty of Management and Accounting, Shahid Beheshti University, Tehran, Iran.

10.22059/frj.2024.377816.1007611

Abstract

Objective
Predicting the future trends in financial markets stands as a critical task for both investors and researchers, given its pivotal role in enabling well-informed decision-making processes and effective risk management strategies. Nevertheless, the realm of stock market dynamics is fraught with inherent complexities and uncertainties, posing a formidable challenge when it comes to achieving accurate predictions. A wide array of predictive modeling techniques have been meticulously investigated, spanning from conventional statistical methodologies to more sophisticated machine learning algorithms. The primary focus of this research endeavor revolves around the predictive analysis of the Tehran Stock Exchange (TSE) Composite Index, wherein a novel hybrid neural network framework is employed. This approach seamlessly integrates multiscale temporal features, with the ultimate objective of bolstering prediction precision and offering profound insights into prevailing market trends and dynamics.
 
Methods
The hybrid neural network architecture that has been put forward integrates the unique capabilities of convolutional neural networks (CNNs) in the realm of feature extraction with the effectiveness of long short-term memory (LSTM) networks in capturing temporal dependencies. The dataset used in this study consists of daily historical data pertaining to the TSE Composite Index, covering a substantial period from the year 1998 to 2022, which has been meticulously gathered, preprocessed, and subsequently partitioned into distinct sets for training and validation purposes. Within the framework of this hybrid neural network model, a sophisticated approach is adopted to harness multiscale temporal features derived from the input data, enabling the generation of highly accurate predictions regarding the future trends of the index. Moreover, to further enhance the performance and resilience of the model, sophisticated feature engineering methodologies are implemented to optimize its overall functionality.
 
Results
The results of the study reveal that while the hybrid neural network model, integrating CNN and LSTM components, demonstrates promising capabilities in predicting the TSE Composite Index, its accuracy falls short compared to competing models, particularly at weekly and monthly time scales. Conversely, the standalone CNN model exhibits superior performance, yielding more accurate predictions of the index's movements. These findings challenge the prevailing notion regarding the efficacy of hybrid neural network models in financial market prediction, highlighting the importance of evaluating alternative modeling approaches based on their specific strengths and limitations.
 
Conclusion
Despite the potential of hybrid neural network models, as demonstrated in previous research, the findings of this study suggest that simpler neural network architectures, such as CNNs, may offer better prediction performance in certain scenarios. To address the limitations identified, future research endeavors could explore alternative model configurations, ensemble methods, or hybrid architectures that combine the strengths of different predictive models. Additionally, incorporating additional market indicators and exploring intraday data sources could further enhance prediction accuracy and robustness. This abstract encapsulates the key findings and implications of the research, providing valuable insights for investors, researchers, and practitioners in the field of financial market prediction.

Keywords

Main Subjects

References

 
Abdi, N., Moradzadeh Fard, N., Ahmadzadeh, K. & Mahmoud, M. (2021). Presenting an optimal portfolio optimization model based on price prediction with LSTM recurrent neural network using cardinality constraints and multi-criteria decision-making methods (case study: Tehran Stock Exchange). Financial Management Perspective, 11(36), 119-143. doi: 10.52547/JFMP.11.36.119 (in Persian)
Addagalla, S., Koppuravuri, S., Krosuri, R., Kunapareddy, M. S., Mallu, S. R. & Rashmi, M. (2023). Stock Market Price Prediction Using Machine Learning Techniques. Paper presented at the 2023 4th International Conference for Emerging Technology (INCET), 2023.
Al Ridhawi, M. & Al Osman, H. (2023). Stock Market Prediction from Sentiment and Financial Stock Data Using Machine Learning. In Canadian AI.
Ali, M., Khan, D. M., Alshanbari, H. M. & El-Bagoury, A. A. H. (2023). Prediction of Complex Stock Market Data Using an Improved Hybrid Emd-Lstm Model. Applied Sciences, 13(3), 1429.
Bajalan, S., Fallahpour, S. & Raeesi, S. (2024). Bank’s Credit Portfolio Optimization Using Actuarial Approach and Artificial Neural Networks. Financial Research Journal, 26(3), 710-733. doi: 10.22059/frj.2021.311064.1007074 (in Persian)
Beheshti-e-Masale-goo, S.M., Afshar-Kazemi, M.A., Haghighat Monfared, J. & Rezaian, A. (2013). Deep learning for stock market forecasting using numerical and textual information (LSTM long-term memory algorithm approach). Financial Engineering and Securities Management, 14(55), 65-87. (in Persian)
Cabessa, J. & Siegelmann, H. T. (2011). Evolving Recurrent Neural Networks Are Super-Turing. Paper presented at the 2011 International Joint Conference on Neural Networks.
Chiriţă, M. (2012). Usefulness of Artificial Neural Networks for Predicting Financial and Economic Crisis. Econ. Appl. Inform, 2, 61-66.
Crowley, J. L. (2021). Machine Learning with Neural Networks. In Eccai Advanced Course on Artificial Intelligence (pp. 39-54). Springer.
Deswal, V. & Kumar, D. (2023). Stock Market Price Prediction Using Machine Learning Techniques: A Review. Paper presented at the 2023 International Conference on Computational Intelligence and Sustainable Engineering Solutions (CISES).
Devkar, C. & Sharma, S. (2023). A Study on Aspect of Artificial Neural Networks for Machine Learning. International Journal of Advanced Research in Science, Communication and Technology, 3(1).
Dhakar, D. S. & Shiwani, S. (2023). Stock Market Prediction Employing Discrete Wavelet Transform and Moving Average Gradient Descent. Paper presented at the Proceedings of the International Conference on Cognitive and Intelligent Computing: ICCIC 2021, Volume 2.
Enriko, I. K., Gustiyana, F. & Krishna, H. (2023). Forecasting Jpfa Share Price Using Long Short Term Memory Neural Network. JAICT, 8, 157.
Fjellström, C. (2022). Long Short-Term Memory Neural Network for Financial Time Series. Paper presented at the 2022 IEEE International Conference on Big Data (Big Data).
Götze, T., Gürtler, M. & Witowski, E. (2023). Forecasting Accuracy of Machine Learning and Linear Regression: Evidence from the Secondary Cat Bond Market. Journal of Business Economics, 93(9), 1629-1660.
Hahn, P. (2019). [Artificial Intelligence and Machine Learning]. Handchir Mikrochir Plast Chir, 51(1), 62-67.
Hao, Y. & Gao, Q. (2020). Predicting the Trend of Stock Market Index Using the Hybrid Neural Network Based on Multiple Time Scale Feature Learning. Applied Sciences, 10(11), 3961.
Hajizadeh Tahan, M., Ghasemzadeh, M. & Rezaeian, M. (2020). An evolutionary attention-based deep long short-term memory for time series prediction. Computational Intelligence in Electrical Engineering, 11(4), 15-28. doi: 10.22108/isee.2020.121597.1334 (in Persian)
Harandi, A., Moeineddin, A., Kaliske, M., Reese, S. & Rezaei, S. (2024). Mixed Formulation of Physics-Informed Neural Networks for Thermo-Mechanically Coupled Systems and Heterogeneous Domains. International Journal for Numerical Methods in Engineering, 125(4), e7388.
Heidari, M. & Amiri, H. (2022). Inspecting the Predictive Power of Artificial Intelligence Models in Predicting the Stock Price Trend in Tehran Stock Exchange. Financial Research Journal, 24(4), 602-623. doi: 10.22059/frj.2022.320064.1007149 (in Persian)
Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735-1780.
Huang, F., Zeng, J., Zhang, Y. & Xu, W. (2020). Convolutional Recurrent Neural Networks with Multi-Sized Convolution Filters for Sound-Event Recognition. Modern Physics Letters B, 34(23), 2050235.
Jiang, X., Zhang, L., Geng, H. & Liu, X. (2023). A Temporal Convolution Memory Network Model for Short-Term Wind Speed Forecasting. Paper presented at the 2023 8th Asia Conference on Power and Electrical Engineering (ACPEE).
Kanagachidambaresan, G. R., Ruwali, A., Banerjee, D. & Prakash, K. B. (2021). Recurrent Neural Network. In Programming with TensorFlow: Solution for Edge Computing Applications (pp. 53-61).
Kohsasih, K. L., Hayadi, B. H., Juliandy, C. & Pribadi, O. (2022). Sentiment Analysis for Financial News Using RNN-LSTM Network. Paper presented at the 2022 4th International Conference on Cybernetics and Intelligent System (ICORIS).
Long, W., Lu, Z. & Cui, L. (2019). Deep Learning-Based Feature Engineering for Stock Price Movement Prediction. Knowledge-Based Systems, 164, 163-173.
Marhon, S. A., Cameron, C. J. F. & Kremer, S. C. (2013). Recurrent Neural Networks. In Handbook on Neural Information Processing (pp. 29-65).
Mojica, F., Villaseñor, C., Alanis, A. Y. & Arana-Daniel, N. (2019). Long Short-Term Memory with Smooth Adaptation. Paper presented at the 2019 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC).
Ogus, D. (2019, August). Long Short-Term Memory: Can Artificial Neural Networks beat Econometric Models? Business Economics. Retrieved from: http://hdl.handle.net/2105/47961
Owusu-Adjei, M., Hayfron-Acquah, J. B., Frimpong, T. & Abdul-Salaam, G. (2023). A Systematic Review of Prediction Accuracy as an Evaluation Measure for Determining Machine Learning Model Performance in Healthcare Systems. medRxiv, 2023.06.01.23290837.
Patil, S., Shankar, V. G., Devi, B., Singh, A. & Upadhyay, N. (2023). Long Short-Term Memory-Driven Recurrent Neural Network for Real-Time Stock Monitoring and Prediction. In Machine Intelligence Techniques for Data Analysis and Signal Processing: Proceedings of the 4th International Conference MISP 2022, Volume 1 (pp. 813-823). Singapore: Springer Nature Singapore.
Rout, A., Bar, A. K., Saha, S. P. & Chaudhuri, A. (2022). Stock Market Prediction Using Machine Learning Algorithm. IJARCCE, 11, 97-116.
Saboor, A., Hussain, A., Agbley, B. L. Y., Li, J. P. & Kumar, R. (2023). Stock Market Index Prediction Using Machine Learning and Deep Learning Techniques. Intelligent Automation & Soft Computing, 37(2).
Sako, K., Mpinda, B. N. & Rodrigues, P. C. (2022). Neural Networks for Financial Time Series Forecasting. Entropy, 24(5), 657.
Sato, D., Matsubayashi, T. & Toda, H. (2022). Prediction Device, Prediction Method, and Prediction Program. Google Patents.
Sezer, O. B. & Ozbayoglu, A. M. (2018). Algorithmic Financial Trading with Deep Convolutional Neural Networks: Time Series to Image Conversion Approach. Applied Soft Computing, 70, 525-538.
Shanmugapriya, D. (2023). A Hybrid Model for Fingerprint Recognition Via LSTM and CNN. Paper presented at the 2023 10th International Conference on Computing for Sustainable Global Development (INDIACom).
Sharif far, A., Khaliliaraghi, M., Raeesi Vanani, I. & Fallahshams, M. (2022). Application of Deep Learning Architectures in Stock Price Forecasting: A Convolutional Neural Network ‎Approach. Journal of Asset Management and Financing, 10(3), 1-20. doi: 10.22108/amf.2022.129205.1673 (in Persian)
Shu, J., Yuan, X., Meng, D. & Xu, Z. (2023). CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence.
Singh, A. & Markande, L. (2023). Stock Market Forecasting Using LSTM Neural Network. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 544-554.
Stamos, M. (2022). Forecasting Stock Market Volatility. The Journal of Portfolio Management, 49.
Tehraniyazdi, N., Vaezi, R., Setayeshi, S. & Raeesi Vanani, I. (2024). Forecasting Insurance Company Commitments with Long Short-Term Memory Models. Financial Research Journal, 26(4), 854-879. doi: 10.22059/frj.2024.367421.1007532 (in Persian)
Thorat, M., Pandit, S. & Balote, S. (2022). Artificial Neural Network: A Brief Study. Asian Journal For Convergence In Technology (AJCT), 8(3), 12-16.
Umer, M., Awais, M. & Muzammul, M. (2019). Stock Market Prediction Using Machine Learning (ML) Algorithms. ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal, 8, 97-116.
Wan, W. D., Bai, Y. L., Lu, Y. N. & Ding, L. (2022). A Hybrid Model Combining a Gated Recurrent Unit Network Based on Variational Mode Decomposition with Error Correction for Stock Price Prediction. Cybernetics and Systems, 1-25.
Xie, Y. (2023). Stock Price Forecasting: Traditional Statistical Methods and Deep Learning Methods. Highlights in Business, Economics and Management, 21, 740-745.
Yao, K. & Zheng, Y. (2023). Fundamentals of Machine Learning. In Nanophotonics and Machine Learning: Concepts, Fundamentals, and Applications (pp. 77-112). Springer.
Yosinski, J., Clune, J., Nguyen, A., Fuchs, T. & Lipson, H. (2015). Understanding Neural Networks through Deep Visualization. arXiv preprint arXiv:1506.06579.
Young, J. D., Andrews, B., Cooper, G. F. & Lu, X. (2020). Learning Latent Causal Structures with a Redundant Input Neural Network. Paper presented at the Proceedings of the 2020 KDD Workshop on Causal Discovery.
Ziyadi, H., Salavati, E. & Lotfi Heravi, M. M. (2023). Housing Price Forecasting Using AI (LSTM). Financial Research Journal, 25(4), 557-576. doi: 10.22059/frj.2023.349924.1007398 (in Persian)
Financial Research Journal
Volume 27, Issue 1
2025
Pages 85-113

Files

Share

How to cite

Statistics