Forecasting Using Combination Of Artificial Neural Networks and box-Jenkins Models : Applied Study(2012)
03-04-2014 05:42
The main objective of this study is to reach an appropriate model to forecast the stock market index EGX30, Using the following methods for forecasting
Neural networks
Time series analysis using Box and Jenkins
Combination of neural networks and time series analysis using previous residuals and estimated values of the ARIMA model
At the end of the study, A comparison between these methods using the criteria for measuring the forecast accuracy, it became clear that the most appropriate method to forecast the index of stock market is Combination using previous residuals and estimated values of the ARIMA model