Research on the Price Prediction Model of the Used New Energy Vehicles Based on PCA-PSO-BP Neural Network

A BP neural network evaluation model based on principal component analysis and particle swarm optimisation algorithm (PCA-PSO-BP) is proposed to address the problems of single selection indicators, excessive reliance on manual detection, and large evaluation error in the existing residual value evaluation of used new energy vehicles. Firstly, the principal component analysis method is used to screen out the most important feature indicators that affect the residual value of new energy vehicles. Then, the particle swarm optimization algorithm is used to optimize the weights and thresholds of the BP neural network. Finally, the selected features are input into the optimized BP neural network to output the residual value evaluation result.The results indicate that the PCA-PSO-BP neural network residual value evaluation model has high prediction accuracy and can provide reference for the current state of the art. The results indicate that the PCA-PSO-BP neural network residual value evaluation model has high prediction accuracy and can provide reference for the current residual value evaluation methods of second-hand new energy vehicles.