A model on forecasting safety stock of ERP based on BP neural network

Safety stock is one of the important parts of logistics management in ERP. This paper attempts to use artificial neural networks to forecast safety stock. Based on the index system of safety stock, this paper constructs a three-level BP neural network to analyze the principle and model of safety inventory. By using the samples to train and inspect the BP neural network, we conclude that the application of BP neural networks is an effective method to forecast safety stock, and can also be used to find the key factors for enterprises to improve their logistics management level.