An Adaptive Approach to Market Development Forecasting

Abstract

In the field of time series models for forecasting, the commonly accepted fact is that no one model could be shown to be superior to all others. An effective time series model for forecasting must incorporate the specific characteristics of the targeted problem domain. This paper proposes a neura network model for market development forecasting In this model, monotonicity and knowledge of seasonal period are incorporated into neural network training. The model is superior to the traditional curve fitting methods, in that it is adaptive in modelling trend and season factors for the time series in cases where the growth curve functions and seasonal functions are a priori unknown. The model is superior to unconstrained neural networks for time series modelling in that random fluctuations can be avoided. An example of forecasting daily sales using the neural network model is demonstrated.