Designing a Stock Trading System Using Artificial Nero Fuzzy Inference Systems and Technical Analysis Approach
This paper has been designed a stock trading systems using Artificial Nero Fuzzy Inference Systems (ANFIS) and technical analysis approach. The proposed model receives 14 last days information and predictes 14 next day's variables' values Simple Moving Average (SMA), Exponential Moving Average (EMA), Moving Average Convergence - Divergence (MACD), Relative Strength (RSI), stochastic oscillator (SO) using ANFIS. Then, the net output are changed to signal of buy and sell after apply trading rules. In the next step, the final signal is created by the sum of generated signals. Thus, bye and sale will propose during the next 14 days. Performance Designed systems were studied for 17 shares. Results showed that the mean of all generated networks Percentage of correct predictions (96/55%) is more than random cases (50%). Given the positive returns SMA ?EMA ?SO and proposed method It's can be results that using these indices of technical analysis can predict trading optimal time of Iran stock market.
Volume (Year): 4 (2014)
Issue (Month): 1 (January)
|Contact details of provider:|| Web page: http://hrmars.com/index.php/pages/detail/Accounting-Finance-Journal|
When requesting a correction, please mention this item's handle: RePEc:hur:ijaraf:v:4:y:2014:i:1:p:76-84. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Hassan Danial Aslam)
If references are entirely missing, you can add them using this form.