Research on Food Price Prediction Based on BP Neural Network Optimized by Immune Algorithm-Particle Swarm Optimization Hybrid Algorithm

Food price prediction is an important part of food supply chain management, and food price prediction is of great research significance and application value. Due to the problems of local optimization and slow learning convergence of traditional back propagation (BP) neural network, this paper proposed a BP neural network optimized by immune algorithm-particle swarm optimization hybrid algorithm (IA-PSO-BP) model for food price prediction, and selected relevant indicators. After neural network training and testing, it is found that compared with the BP neural network model optimized by particle swarm optimization algorithm (PSO-BP), the BP neural network model optimized by immune algorithm (IA-BP) and the BP neural network model, the IA-PSO-BP neural network model has the smallest prediction error and the highest accuracy. Compared with PSO-BP neural network model, IA-BP neural network model and BP neural network model, the mean absolute error (MAE) of IA-PSO-BP neural network model is reduced by 39.20%, 67.00% and 140.80%, the root mean square error (RMSE) is reduced by 39.60%, 67.50% and 141.20%, and the mean absolute percentage error (MAPE) is reduced by 0.46%, 0.79% and 1.67%. The predicted value of the IA-PSO-BP neural network model is closest to the actual value, which is more accurate to predict the actual food price. The conclusion shows that the IA-PSO-BP neural network model is a forecasting tool with higher accuracy and stronger applicability, and can be better used in food price prediction.