Introduction - If you have any usage issues, please Google them yourself
The cement industry is one of the most important and profitable industries in Iran and great
content of financial resources are investing in this sector yearly. In this paper a GMDH-type
neural network and genetic algorithm is developed for stock price prediction of cement sector.
For stocks price prediction by GMDH type-neural network, we are using earnings per share
(EPS), Prediction Earnings Per Share (PEPS), Dividend per share (DPS), Price-earnings ratio
(P/E), Earnings-price ratio (E/P) as input data and stock price as output data. For this work, data
of ten cement companies is gathering Tehran stock exchange (TSE) in decennial range
(1999-2008). GMDH type neural network is designed by 80 of the experimental data. For
testing the appropriateness of the modeling, reminder of primary data were entered into the
GMDH network. The results are very encouraging and congruent with the experimental results.