Forecasting time series using logical combinations of neural-based networks

Forecasts are the basis for planning and decision making. The more accurate the organization´s forecasts, the better prepared it will be to take advantage of future opportunities and to reduce potential risks. Thus, it should come as no surprise that there is a tremendous number of statistical prediction algorithms already in existence. However, most of them are useful only when the time series exhibit little trend or seasonal variations but a great deal of irregular or random variation. Therefore, the objective of this paper is to propose a new intelligent forecasting technique which is constructed by combining n-trained neural-based network together. The experimental results based on simulated data show a significant improvement in forecasting accuracy