Fuzzy Delphi and Back- Propagation model for sale forecasting in Wood and Paper industry Case: Mazandaran Wood & Paper

Nowadays quantitative methods have become very important tools for forecasting purposes in markets as for improved decisions and investment. Forecasting accuracy is one of the most important factors involved in selecting method; Artificial Neural Network (ANNs) are flexible computing frameworks that can be applied to a wide range offorecasting with a high degree of accuracy. In this research, Fuzzy logic and Artificial Neural Network are integrated in to the Fuzzy Back- Propagation Network (FBPN) for sales forecasting in Wood and Paper industry. The proposed system is evaluated through the real world data provided by a Wood an d Paper company and experimentalresults indicate that the Fuzzy Back- Propagation approach outperforms are better other two different forecasting models (Linear Regression and ARIMA time series model) in MAPE measures.