Forecasting of Government's Financial Educational Fund by Using Neural Networks Model

Abstract

Forecasting method using neural networks has been advocated as an alternative to traditional statistical forecasting in recent years. The paper built a feed-forward neural network model to forecast the values of governmentpsilas financial educational fund (GFEF) in year 2010. On the basis of data processing, the structure of neural networks was given. The algorithm that adopted as a learning phase in the model was a fast one differing from that of the steep decent algorithm. The forecasts obtained from neural networks model were compared with the data forecasting by experts, and the error curve and the auto-adjusting curve of learning rate were also illustrated. The results show that the model was very effective.