Linear Regression and Artificial Neural Networks in Stock Price Forecasting: A Case Study of Isfahan Steel

Sattar Salimian 1, Ehsan Rostami 1, Salah Salimian 2, Hazhir Pourmahmud 3

1 Razi University, Kermanshah, Iran
2 University of Kurdistan, Sanandaj, Iran
3 Schmalkalden University, Thüringen, Germany

Abstract

Stock price prediction constitutes a fundamental challenge in financial economics, with substantial implications for investment efficiency, market stability, and capital allocation. This study addresses the need for robust forecasting methodologies through a comparative analysis of classical statistical and machine learning approaches. The primary objective is to empirically evaluate and contrast the predictive accuracy of multivariate linear regression and artificial neural networks (ANN) for firm-level equity forecasting. The central hypothesis posits that the ANN, by virtue of its capacity to model complex nonlinearities, will demonstrate superior predictive performance relative to linear regression, which remains constrained by parametric and additive assumptions. The research employs a comprehensive dataset comprising 547 observations across 11 financial and economic variables for Isfahan Steel Company. A rigorous methodological framework was implemented, incorporating data preprocessing to address multicollinearity and non-normality, followed by multivariate linear regression estimation using SPSS and a feedforward ANN trained with resilient backpropagation (Rprop) and L2 regularization. The empirical results demonstrate that the ANN model achieves superior predictive accuracy (R² = 0.934) compared to linear regression (R² = 0.893), effectively capturing the complex nonlinear relationships inherent in financial time series and confirming the research hypothesis. The theoretical contribution lies in extending asset pricing literature by delineating the limitations of linear paradigms in explaining price formation complexity. Practically, the findings suggest that policymakers and financial analysts should integrate ANN-based forecasting tools into market monitoring and risk assessment frameworks, while regulatory bodies should promote transparency in predictive model development to enhance market confidence and informed decision-making.

Keywords

linear networks; stock price forecasting regression; artificial neural; multilayer perceptron; financial time series.

JEL classification

References

1. Welch, I., Goyal, A. (2008). A comprehensive look at the empirical performance of equity premium prediction. The Review of Financial Studies, Vol. 21, Issue 4, 1455–1508. doi.org/10.1093/rfs/hhm014

          2. Rapach, D.E., Strauss, J.K., Zhou, G. (2013). International stock return predictability: What is the role of the United States? The Journal of Finance, Vol. 68, Issue 4, 1633–1662. doi.org/10.1111/jofi.12041

          3. Atsalakis, G.S., Valavanis, K.P. (2009). Surveying stock market forecasting techniques – Part II: Soft computing methods. Expert Systems with Applications, Vol. 36, Issue 3, Part 2, 5932–5941. doi.org/10.1016/j.eswa.2008.07.006

          4. Fama, E.F. (1970). Efficient capital markets: A review of theory and empirical work. The Journal of Finance, Vol. 25, No. 2, 383–417. doi.org/10.2307/2325486

          5. Lim, K.P., Hooy, C.W. (2013). Non-Linear Predictability in G7 Stock Index Returns. The Manchester School, Vol. 81, Issue 4, 620–637. doi.org/10.1111/j.1467-9957.2012.02303.x

          6. Huang, W., Nakamori, Y., Wang, S.Y. (2005). Forecasting stock market movement direction with support vector machine. Computers & Operations Research, Vol. 32, Issue 10, 2513–2522. doi.org/10.1016/j.cor.2004.03.016

          7. Leung, M.T., Daouk, H., Chen, A.S. (2000). Forecasting stock indices: a comparison of classification and level estimation models. International Journal of Forecasting, Vol. 16, Issue 2, 173–190. doi.org/10.1016/S0169-2070(99)00048-5

          8. Henrique, B.M., Sobreiro, V.A., Kimura, H. (2019). Literature review: Machine learning techniques applied to financial market prediction, Expert Systems with Applications, Vol. 124, 226–251. doi.org/10.1016/j.eswa.2019.01.012

          9. Bekaert, G., Harvey, C.R. (2017). Emerging equity markets in a globalizing world. SSRN Electronic Journal, 2344817. doi.org/10.2139/ssrn.2344817

          10. Fama, E.F., French, K.R. (1993). Common risk factors in the returns on stocks and bonds. Journal of Financial Economics, Vol. 33, Issue 1, 3–56. doi.org/10.1016/0304-405X(93)90023-5

          11. Cavalcante, R.C., Brasileiro, R.C., Souza, V.L., Nobrega, J.P., Oliveira, A.L. (2016). Computational intelligence and financial markets: A survey and future directions. Expert Systems with Applications, Vol. 55, 194–211. doi.org/10.1016/j.eswa.2016.02.006

          12. Nti, I. K., Adekoya, A.F., Weyori, B.A. (2020). A systematic review of fundamental and technical analysis of stock market predictions. Artificial Intelligence Review, Vol. 53, Issue 4, 3007–3057. doi.org/10.1007/s10462-019-09754-z

          13. Sezer, O.B., Gudelek, M.U., Ozbayoglu, A.M. (2020). Financial time series forecasting with deep learning: A systematic literature review: 2005–2019. Applied Soft Computing, Vol. 90, 106181. doi.org/10.1016/j.asoc.2020.106181

          14. Wang, J.J., Wang, J.Z., Zhang, Z.G., Guo, S.P. (2012). Stock index forecasting based on a hybrid model. Omega, Vol. 40, Issue 6, 758–766. https://doi.org/10.1016/j.omega.2011.07.008

          15. Ballings, M., Van den Poel, D., Hespeels, N., Gryp, R. (2015). Evaluating multiple classifiers for stock price direction prediction. Expert systems with Applications, Vol. 42, Issue 20, 7046–7056. doi.org/10.1016/j.eswa.2015.05.013

          16. Krauss, C., Do, X.A., Huck, N. (2017). Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500. European Journal of Operational Research, Vol. 259, Issue 2, 689–702. doi.org/10.1016/j.ejor.2016.10.031

          17. De Faria, E.L., Albuquerque, M.P., Gonzalez, J.L., Cavalcante, J.T.P., Albuquerque, M.P. (2009). Predicting the Brazilian stock market through neural networks and adaptive exponential smoothing methods. Expert Systems with Applications, Vol. 36, Issue 10, 12506–12509. doi.org/10.1016/j.eswa.2009.04.032

          18. Pai, P.F., Lin, C.S. (2005). A hybrid ARIMA and support vector machines model in stock price forecasting. Omega, Vol. 33, Issue 6, 497–505. https://doi.org/10.1016/j.omega.2004.07.024

          19. Chen, Y., Hao, Y. (2017). A feature weighted support vector machine and K-nearest neighbor algorithm for stock market indices prediction. Expert Systems with Applications, Vol. 80, 340–355. doi.org/10.1016/j.eswa.2017.02.044

          20. Rahnemoon, P.T., Akbar, M.S.S., Asgari, M. (2024). Modeling and Monthly Price Forecasting of Steel in Iran. Stable Economy Journal, Vol. 4, Issue 4, 60–95. doi.org/10.22111/SEDJ.2024.47309.1417

          21. Moseane, O., Tsoku, J.T., Metsileng, D. (2024). Hybrid time series and ANN-based ELM model on JSE/FTSE closing stock prices. Frontiers in Applied Mathematics and Statistics, Vol. 10, 1454595. doi.org/10.3389/fams.2024.1454595

          22. Kim, K.J. (2003). Financial time series forecasting using support vector machines. Neurocomputing, Vol. 55, Issue 1-2, 307–319. doi.org/10.1016/S0925-2312(03)00372-2

          23. Wijesinghe, G.W.R.I., Rathnayaka, R.M.K.T. (2020). ARIMA and ANN Approach for forecasting daily stock price fluctuations of industries in Colombo Stock Exchange, Sri Lanka. Proceedings of 2020 5th International Conference on Information Technology Research (ICITR). IEEE, 1–7. doi.org/10.1109/ICITR51448.2020.9310826

          24. Wijesinghe, G.W.R.I., Rathnayaka, R.M.K.T. (2020). Stock market price forecasting using ARIMA vs ANN; a case study from CSE. Proceedings of 2020 2nd International Conference on Advancements in Computing (ICAC), Vol. 1. IEEE, 269–274). https://doi.org/10.1109/ICAC51239.2020.9357288

          25. Zhang, G., Patuwo, B.E., Hu, M.Y. (1998). Forecasting with artificial neural networks: The state of the art. International Journal of Forecasting, Vol. 14, Issue 1, 35–62. doi.org/10.1016/S0169-2070(97)00044-7

          26. Varshney, S., Srivastava, P. (2023). A comparative study of future stock price prediction through artificial neural network and ARIMA modelling. NMIMS Management Review, Vol. 31, Issue 4, 229–239. doi.org/10.1177/09711023241230367

          27. Shi, C., Zhuang, X. (2019). A study concerning soft computing approaches for stock price forecasting. Axioms, Vol. 8, Issue 4, 116. doi.org/10.3390/axioms8040116

          28. Khan, A.H., Shah, A., Ali, A., Shahid, R., Zahid, Z.U., Sharif, M.U., Zafar, M.H. (2023). A performance comparison of machine learning models for stock market prediction with novel investment strategy. PLoS ONE, Vol. 18, Issue 9, e0286362. doi.org/10.1371/journal.pone.0286362

          29. Shahi, T.B., Shrestha, A., Neupane, A., Guo, W. (2020). Stock price forecasting with deep learning: A comparative study. Mathematics, Vol. 8, Issue 9, 1441. doi.org/10.3390/math8091441

          30. Jia, Y., Anaissi, A., Suleiman, B. (2024). ResNLS: An improved model for stock price forecasting. Computational Intelligence, Vol. 40, Issue 1, e12608. https://doi.org/10.1111/coin.12608

          31. Yuan, X., Guo, Y., Gu, S., Wang, J., Qi, A., Li, S., Zhao, L. (2025). TFE-HMM: Combining State Transitions and Price Trends for Stock Price Forecasting. Expert Systems with Applications, Vol. 288, 128192. doi.org/10.1016/j.eswa.2025.128192

          32. Kwembe, T.A. (2025). Multivariate Linear Model for Data Analysis and Machine Learning and the Theory and Practice of Eigenvalues in Mitigating Multicollinearity. In: Bridging Eigenvalue Theory and Practice-Applications in Modern Engineering. Edited by B. Carpentieri. IntechOpen, 89–95. doi.org/10.5772/intechopen.1007814

          33. Box, G.E., Pierce, D.A. (1970). Distribution of residual autocorrelations in autoregressive-integrated moving average time series models. Journal of the American Statistical Association, Vol. 65, Issue 332, 1509–1526. doi.org/10.1080/01621459.1970.10481180

          34. Zou, H., Hastie, T. (2005). Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society Series B: Statistical Methodology, Vol. 67, Issue 2, 301–320. doi.org/10.1111/j.1467-9868.2005.00503.x

          35. Taylor, S.J., Letham, B. (2018). Forecasting at scale. The American Statistician, Vol. 72, Issue 1, 37–45. doi.org/10.1080/00031305.2017.1380080

About Authors

Sattar Salimian

PhD Student in Resource Economics, Department of Economics, Razi University, Kermanshah, Iran (Kermanshah Province, Kermanshah, Zakariya Razi Blvd, Iran); ORCID orcid.org0000-0003-1345-3829 e-mail: sattar.salimian@yahoo.com

Ehsan Rostami

PhD in Economics, Department of Economics, Razi University, Kermanshah, Iran (Kermanshah Province, Kermanshah, Zakariya Razi Blvd, Iran); ORCID orcid.org0009-0000-0973-8296 e-mail: rostamiehsan1404@gmail.com

Salah Salimian

Postdoctoral Researcher in Economics, Department of Economics, Faculty of Humanities and Social Sciences, University of Kurdistan, Sanandaj, Iran (Kurdistan Province, Sanandaj, Iran); ORCID orcid.org0000-0002-4938-950X e-mail: salahsalimian@yahoo.com

Hazhir Pourmahmud

Master of Finance, Schmalkalden University, Thüringen, Germany (Blechhammer 9, 98574 Schmalkalden, Germany); ORCID orcid.org0009-0007-8005-3063 e-mail: Hazhir2pourmahmud@gmail.com

For citation

Salimian, S., Rostami, E., Salimian, S., Pourmahmud, H. (2026). Linear Regression and Artificial Neural Networks in Stock Price Forecasting: A Case Study of Isfahan Steel. Journal of Applied Economic Research, Vol. 25, No. 2, 625-654. doi.org/10.15826/vestnik.2026.25.2.021

Article info

Received January 28, 2026; Revised February 21, 2026; Accepted February 23, 2026.

DOI: http://dx.doi.org/10.15826/vestnik.2026.25.2.021

Download full text article: