Forecasting Educational Expenditure Based on Radial Basic Function Neural Network and Principal Component Analysis

In this paper, radial basic function neural network (RBFNN) is used for educational expenditure forecasting. But the input space is heavily self-correlated, and the input numbers are too many, in that case, canters of the neurons will be overlapped, therefore the accuracy of forecasting by RBFNN will be descendant. Principal component analysis is a dimensionality reduction technique based on extracting the desired number of principal components of multidimensional data. Application of radial basic function neural network based on principal component analysis in educational expenditure forecasting demonstrates the effectiveness and feasibility of the proposed method.