A decision support system for sales forecasting through fuzzy neural networks with asymmetric fuzzy weights

Sales forecasting plays a very prominent role in business strategy. Numerou s investigations addressing this problem have generally employed statistica l methods, such as regression or autoregressive and moving average (ARMA). However, sales forecasting is very complicated owing to influence by intern al and external environments. Recently, artificial neural networks (ANNs) h ave also been applied in sales forecasting since their promising performanc es in the areas of control and pattern recognition. However, further improv ement is still necessary since unique circumstances, e.g., promotion, cause a sudden change in the sales pattern. Thus, this study utilizes fuzzy logi c a proposed fuzzy neural network (FNN) for the sake of learning fuzzy IF-T HEN rules obtained from the marketing experts with respect to promotion. Th e result from FNN is further integrated with the forecast from ANN using th e time series data and the promotion length through the other ANN. Model ev aluation results indicate that the proposed system can more accurately perf orm than the conventional statistical method and single ANN. (C) 1998 Elsev ier Science B.V. All rights reserved.