Inspecting the Predictive Power of Artificial Intelligence Models in Predicting the Stock Price Trend in Tehran Stock Exchange

Document Type : Research Paper


1 Assistant Prof., Department of Economics, Faculty of Economics and Finance, Khatam University, Tehran, Iran.

2 MSc. Student, Department of Economics, Faculty of Humanities, Khatam University, Tehran, Iran.



Objective: Time series prediction methods based on artificial intelligence have been widely developed in recent years. Given that these data have large dimensions in the field of investment and stock price forecasting, traditional data analysis methods have low predictive power. This study examines the predictive power of a variety of models based on machine learning in the Tehran Stock Exchange.
Methods: After collecting data from 150 large companies listed on the Tehran Stock Exchange from 2012 to 2021, we want to predict the stock price trend- the movement direction of the price- and then validate each method and compare their accuracy. In these methods, we allocate part of the data to the learning section and the rest to the test section. We take these periods as training and trading sets. These methods include linear models, autocorrelation models, trees, and neural networks.
Results: Deep learning models show better performance than other models and have an accuracy of about 70 percent. Also, we show the time series of the best-performance model accuracy of portfolios of some large industries. The best-performance model of DL in this study is Recurrent Neural Networks. In addition, we show that shallow learning models have higher accuracy and most models perform better in predicting descending stock trends.
Conclusion: In this study, after trying to use the models very carefully, the result is that these models do not provide stunning results to investors.


Afsharirad, E., Alavi, S. E., & Sinaei, H. (2018). Developing an Intelligent Model to Predict Stock Trend Using the Technical Analysis. Financial Research Journal20(2), 249-264. (in Presian)
Bianchi, D., Büchner, M., & Tamoni, A. (2020). Bond risk premia with machine learning. WBS Finance Group Research Paper, (252).
Breiman, L. (2001). Random forests. Machine learning45(1), 5-32.
Brogaard, J., & Zareei, A. (2019). Machine learning and the stock market. Available at SSRN 3233119.
Campbell, J. Y., & Thompson, S. B. (2008). Predicting excess stock returns out of sample: Can anything beat the historical average? The Review of Financial Studies21(4), 1509-1531.
Chen, L., Pelger, M., & Zhu, J. (2019). Deep learning in asset pricing. Available at SSRN 3350138.
Cochrane, J. H. (2011). Presidential address: Discount rates. The Journal of finance66(4), 1047-1108.
Dorodi, D., & Abrahimi, S. B. (2017). Presenting a new hybrid method for predicting the Stock Exchange price index. Financial Research Journal, 18 (4), 612-632. (in Persian)
Fakhari, H., Valipour Khatir, M. & Mousavi, M. (2017). Investigating Performance of Bayesian and Levenberg-Marquardt Neural Network in Comparison Classical Models in Stock Price Forecasting. Financial Research Journal, 19 (2), 229-318. (in Persian)
Fallahpour, S., & Hakimian, H. (2019). Paired Trading Strategy Optimization Using the Reinforcement Learning Method: Intraday Data of Tehran Stock Exchange. Financial Research Journal, 21(1), 19- 34. (in Persian)
Fama, E. F., & French, K. R. (1992). The cross‐section of expected stock returns. The Journal of Finance47(2), 427-465.
Fama, E. F., & French, K. R. (1993). Common risk factors in the returns on stocks and bonds. Journal of Financial Economics, 33, 3-52.
Fama, E. F., & French, K. R. (2015). A five-factor asset pricing model. Journal of financial economics116(1), 1-22.
Giglio, S., & Xiu, D. (2017). Inference on risk Premia in the presence of omitted factors (No. w23527). National Bureau of Economic Research.
Graves, A. (2013). Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850.
Gu, S., Kelly, B., & Xiu, D. (2020). Empirical asset pricing via machine learning. The Review of Financial Studies33(5), 2223-2273.
Harvey, C. R., Liu, Y., & Zhu, H. (2016). … and the cross-section of expected returns. The Review of Financial Studies29(1), 5-68.
Heaton, J. B., Polson, N. G., & Witte, J. H. (2017). Deep learning for finance: deep portfolios. Applied Stochastic Models in Business and Industry33(1), 3-12.
Henriksson, R. D., & Merton, R. C. (1981). On market timing and investment performance. II. Statistical procedures for evaluating forecasting skills. Journal of business, 513-533.
Huck, N. (2009). Pairs selection and outranking: An application to the S&P 100 index. European Journal of Operational Research196(2), 819-825.
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 Research259(2), 689-702.
Malkiel, B. G., & Fama, E. F. (1970). Efficient capital markets. A review of theory and empirical work Journal of Finance, 25, 383, 417.
Markowitz, H. (1952). Portfolio selection. The journal of finance, 7(1), 77-91.
Medsker, L., & Jain, L. C. (Eds.). (1999). Recurrent neural networks: design and applications. CRC press.
Olah, C. (2015). Understanding lstm networks.
Seif, S., Jamshidinavid, B., Ghanbari, M. & Esmaeilpour, M. (2021). Predicting Stock Market Trends of Iran Using Elliott Wave Oscillation and Relative Strength Index. Financial Research Journal, 23(1), 134-157. (in Persian)
Sirignano, J., Sadhwani, A., & Giesecke, K. (2016). Deep learning for mortgage risk. arXiv preprint arXiv:1607.02470.
Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing50, 159-175.