Combination of Grey System and Neural Network Based Sports Achievement Forecasting Algorithm

This paper presents two novel forecasting algorithms for sports achievement based on combination of grey model and neural network: (1) GM-NN1: Firstly, the error sequence is obtained by GM(1,1) model using original data sequence of sports achievement, and then in order to gain a forecasting error sequence, the neural network is built up to train the regression of error sequence. This new model corrects the error of GM(1,1) model prediction using neural network, and its accuracy has been significantly improved. (2) GM-NN2: This model uses the partial-data sequence of the original sports achievement data to create partial-data GM(1,1) model group, and build a neural network to establish the nonlinear relationship between the fitted values and original data, the generated network estimates the forecasting development trend of the partial-data GM(1,1) model group, and achieves better results in the medium-and long-term forecast for sports achievement.