An Improved Neural Networks Prediction Model and Its Application in Supply Chain

Accurate prediction of demand is the key to reduce the cost of inventory for an enterprise in Supply Chain. Based on recurrent neural networks, a new prediction model of demand in supply chain is proposed. The learning algorithm of the prediction is also imposed to obtain better prediction of time series in future. In order to validate the prediction performance of recurrent neural networks, a simulated time series data and a practical sales data have been used. By comparing the prediction result of Multi-Layer feedback neural networks and recurrent neural networks, it can be shown that the recurrent neural networks prediction model can help in improving the prediction accuracy. [Nature and Science. 2006;4(3):23-27].