Integration of Fuzzy Delphi, Fuzzy Clustering and Back-Propagation Neural Networks with Adaptive Learning Rate for Sales Forecasting in ERP Architecture

Sales forecasting, which has been investigated by various researchers, is a very complicated environment. Control and evaluation of future sales still seem concerned both researchers and policy makers and managers of companies. In recent years, there has been a strong tendency by companies to use centralized management systems like Enterprise resource planning (ERP). ERP systems offer a comprehensive and simplified process managements and extensive functional coverage. Sales management module is an important element business management of ERP. this research propose an intelligent hybrid sales forecasting system based on Fuzzy Delphi Method, fuzzy clustering and Back-propagation (BP) Neural Networks with adaptive learning rate in ERP architecture (Delphi-FCBPN-ERP). An example based on an industrial company that manufactures packaging is used to evaluate the proposed intelligent system. Experimental results show that the proposed approach is superior then the traditional approaches