A new method for training the artificial neural network is presented.In this method,the genetic algorithm(GA),a general-purpose global search algorithm is used to train the network with updating the weights to minimize the error between the network output and the desired output.Then the back propagation(RP) algorithm is used to further train the artificial neural network.The method is used to speed up the convergence and improve the performance.Experiment shows that the GA-neural network prediction model is good prediction precision.