Evolving neural network for printed circuit board sales forecasting

Abstract

Printed circuit board industry plays an important role in Taiwan's economy, but severe inventory stacking and material lacking problems still exist. However, the occurrence of these problems is likely to be decreased via establishing an accurate demand forecasting system. Thus, an Evolving Neural Network (ENN) forecasting model by integrating Genetic Algorithms and Neural Network is developed in this research. Along with trend and seasonal factors considered by Winter's model, effective economical factors are chosen by the Grey Relation Analysis. The numerical data of these factors and actual demand of the past 5 years are input into the training stage of ENN, while the comparison with other models is evaluated on testing stage. The experimental result shows that the performance of ENN is superior to traditional statistical models and Back Propagation Network. The ENN provides a promising solution to the forecasting problem for relevant industries.