An Adaptive Demand Forecasting Approach using Datamining Technique

Demand forecasting for Supply Chain Planning (SCP) is essential highly to obtain forecasting accuracy and real time outputs reflecting structural market changes. In this study, an adaptive demand forecasting approach adopting the data mining technique which detects the correlations between target factors and other related elements, is proposed. Including the scheme of the time series analysis based on the state space approach, this approach has two characteristic points. One is the state space which is formulated by principal components composed from various market ele-ments. The other is the self organization of the state space using a neural network. In regard to the latter feature, we previously introduced the modified General Method of Data Handling (modified GMDH) method into the self organization mechanism. Consequently, we achieved significantly higher accuracy using this approach compared to the previous approach