A combination forecasting method of grey neural network based on genetic algorithm

Abstract

Faced with the rapid-changing market under customization mode, the ability to predict market development in advance and formulate corresponding production scheduling plans is of great significance for companies to take lead in competition. The current forecasting algorithm based on grey neural network relies on continuous and much sample data to accurately predict product demand, resulting in low accuracy and poor reliability of the prediction results of nonlinear small-data system. In this paper a grey neural network prediction method coupled with genetic algorithm is proposed. Firstly, a grey neural network model for forecasting product order demand is constructed based on the grey model and neural network theory. Secondly, the elevator product is taken as an example to demonstrate the prediction performance of the model. Lastly, the genetic algorithm is used to iteratively optimize the network weights and thresholds of the model in order to solve the premature convergence and improve the global optimization capability in the prediction process. The results show that the accuracy and robustness of the optimized product prediction model are improved, which verifies the feasibility of the designed method.