Fuzzy-neural model with hybrid market indicators for stock forecasting
Fuzzy-neural model with hybrid market indicators for stock forecasting
sanaz sarafraz1 farid sefati2 alireza ghiyasvand3
1) Department of financial management, Boroujerd Branch ,Islamic Azad University, Boroujerd, Iran
2) 2,3Department of Accounting, Boroujerd Branch, Islamic Azad University, Boroujerd, Iran
3) 2,3Department of Accounting, Boroujerd Branch, Islamic Azad University, Boroujerd, Iran
IOI Code
:
XYDG-AGFEA
Publication :
1ST International Conference on Researches in Accounting, Economics, Management & Humanities (meaconf.com/1st)
Abstract :
Investors use prediction models to make decision about determination of assets value, risk estimation, evaluation of stock price and .... Some of the reseaches conducted to predict the stock price based on technical indices that are dependent to historical data of stock price with no satisfactory performance. Effect of using the technical combined market indices, foundmental indices and experts views about prediction of stock price are studied in the research. The main purpose of the present research is to improve the accuracy of the prediction of stock price by presentation of combined modek of technical, foundmental (quantitative data) indices and experts views (qualitative data) and by using Fuzzy neural architecture. For this reason data of Steel Company that is listed on Tehran stock exchange during 2015 financial year is studied. In ordr to analyze the price and its prediction, three models of artificial neural network and hybrid model, and combinition of artificial neural networks and Fuzzy logic as the third model are studied and their errors are calculated and they are compared based on priority of errors. The results showed the better performance of developed hybrid model to predict the stock price based on experts views with technical and foundmental indices by using Fuzzy neural architecture in order to accuracy of prediction of stock price than traditional usage of neural network model with technical indices.
Keywords : prediction stock price artificial neural networks fuzzy logic