Document Type : Original Article


1 M.A., Esfahan University.

2 Assistant Professor, Esfahan University.


This study examines the week-form efficiency and predictability of lead market using both technical and fundamental approaches and tries to find the best method to be used for predicting the lead price. To this end, we first test the week-form efficiency and show that the time series of prices does not follow a random walk, so we can conclude that the week form information efficiency does not hold in the lead market and the lead price is predictable. Then a range of linear and non-linear methods have been used to peredit lead price. The data for lead price and fundamental factors are weakly observations over the first week of 2005 up to the last week of 2015 and has been gathered using a variety of resources including LME, SGS, ILZSG, FRED websites. The results show that in the technical approach, the hybrid GMDH and genetic algorithm model is the best model in terms of the root mean square error (RMSE) and mean absolute percentage error (MAPE).  In the fundamental approach, two stage least-square is the best model in terms of RMSE and MAPE. As the market is not efficient, the next question is if the market participant can apply investment strategies to exploit the peredictability in this market in their trades. The question may be investigated by future reaseach.


1. Abbaspour, M. (2002). Iran Khodro Stock Price Prediction using Neural Network, Tehran University of Technology, Faculty of Engineering, Shahid Beheshti University (in Persian).
2. Andonie, R. (2010). Extreme Data Mining: Inference from small Datasets. International Journal of Computers Communication & Control, 5, 280-291.
3. Atsalakis, G. S. (2016). Using computational intelligence to forecast carbon prices. Applied Soft Computing, 43, 107-116.
4. Azadeh A., Moghaddam, M., Khakzad, M., & Ebrahimipour, V. (2012). A flexible neural network-fuzzy mathematical programming algorithm for improvement of oil price estimation and forecasting. Computers & Industrial Engineering, 62(2), 421-430.
5. Demuth, H. B., Beale, M. H., De Jess, O., & Hagan, M. T. (2014). Neural network design. Martin Hagan.
6. Eberhart, R. C., & Kennedy, J. (1995). A new optimizer using particle swarm theory. In Proceedings of the sixth international symposium on micro machine and human science, 1, 39-43.
7. Fakhraei, H. (2007). Comparison of water demand forecasting using structural patterns, time series and, neural networks. Master's thesis, Faculty of Economics, University of Tehran (In Persian).
8. Fama, E. F. (1970). Efficient Capital Market: A Review of Theory and Empirical Work. The Journal of Finance, 25(2), 383-417.
9. Fan, X., Wang, L., & Li, S. (2016). Predicting chaotic coal prices using a multi-layer perceptron network model. Resources Policy, 50, 86-92.                  
10. Farlow, S. J. (1981). The GMDH algorithm of Ivakhnenko. The American Statistician, 35(4), 210-215.
11. Fathabadi, Zahra and Basiri, Mohamma Hossein (2012). Copper price forecasting using the neural network, the first conference of Iranian Mining Technologies (in Persian).
12. Hejazi, S. H., & Saberi Ghamarposhti, M. (2016). Prediction Bahar Azadi full bodied gold coin price with neural network GMDH model, The First International Conference on the New Paradigms of Business Intelligence and Organizational Management, Tehran, Shahid Beheshti University (in Persian).
13. JahanKhani, A., & Parsaiyan, A. (1996). Tehran Stock Exchange. Tehran: Tehran University Press Faculty Publishing (In Persian).
14. Jones, C. P. (1996). Investment Analysis and Management, 4th Edition, John Willey and Sons. Inc, New York.
15. Kasabov, N. K. (1996). Foundations of neural networks, fuzzy systems, and knowledge engineering. Marcel Alencar.
16. Ljung, G. M. & Box, G. E. P. (1978). On a Measure of Lack of Fit in Time Series Models. Biometrika, 65(2): 297-303.
17. Manavi, S. E., & Karimi, A. (2014). A New Approach in Data Mining to Forecasting metals Prices Based on Firefly Algorithm and Neural Network. National Conference on Computer Engineering Research (In Persian).
18. Mansourfar, Karim. (2006). Statistical Progress with Computer Programs. Tehran, University of Tehran: 173 (in Persian).
19. Moeini, A., Abrishami, H., & Ahrari M. (2015). GMDH Neural Network Application in Energy Economics. Azar Barzzin, First Printing, Tehran (In Persian).
20. Monfared, Soheil Almasi, and David Enke. (2014). Volatility Forecasting Using a Hybrid GJR-GARCH Neural Network Model,  Procedia Computer Science, 36, 246-253.
21. Morovvati Sharifabadi, A., & Khanche mehr, R. (2014). Find the most suitable artificial neural network structure using the Taguchi experiments design method. Journal of Industrial Management Percpective, 13: 121-142 (In Persian).
22. Murphy, J. J. (1999). Technical analysis of the financial markets: A comprehensive guide to trading methods and applications. NewYork: Institue of Finance.
23. Nazari, M., Tabatabaei Kaljahi, S. V., & Ahrari, M. (2013). Comparison of three methods of estimating the price of a computer in the Tehran market: pleasure regression (hedonic), Recursive neural network and GMDH neural network. Journal of Business Management Perspective, 13, 45-60 (In Persian)
24. Okanel baverman (2008). Time series prediction". Translation by Reza Shiva. Tehran: Institute of Business Studies and Research (in Persian).
25. Parchami, B., Nematzadeh, H., & Shahverdi, R. (2016). Prediction of stock return based on financial variables with the approach of neural networks, International Conference on Computer Engineering and Information Technology, Tehran, Permanent Secretariat of the Conference (In Persian).
26. Sadeghi, H., Sohrabi Vafa, H. & Noori, F. (2013). Applications of Neural Network Based on Genetic Algorithm for Long Term Energy Demand Forecasting. Journal of Applied Theories of Economics, 1(2), 29-52 (In Persian).
27. Shohadaei, M. A. (2007). Fundamental Analysis in the Capital Market. Tehran: Chalesh Publications (In Persian).
28. Thaghafi Kolvanegh, R. (2009). Evaluating the Effectiveness of Using Technical Analysis Patterns in Tehran Stock Exchange. Master's thesis. University of Esfahan. School of Administrative Sciences and Economics (In Persian).
29. ZivariPaydar, S., & Saberi Kamarposhti, M. (2016). Influence of Inflation and Steel Rate Changes on Vehicle stock Market Changes Using the GMDH Model Artificial Neural Networks, The First International Conference on the New Paradigms of Business and Organizational Management, Tehran, Shahid Beheshti University (In Persian).