Research on the Forecast Model of Electricity Power Industry Loan Based on GA-BP Neural Network

According to the quantitative forecast of the investment changes of the loan in electric power industry, we put forward a kind of forecast model that based on GA-BP neural network. According to the sliding window method, we use each of the electric power industry structure to form part of the loan of the linear correlation of continuous time sequence, put it as data sample additional episodes GA-BP neural network, and then eventually get prediction model. Finally, through a bank nearly 20 years the electric power industry loan fund investment data changes of experiments show that the forecasting model is effective, the experimental results show that based on GA-the BP neural network of prediction model is adopted to overcome the fitting compared with the traditional forecasting method, and obviously improve the forecast accuracy. of the investment changes. (C) 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of the organizing committee of 2nd International Conference on Advances in Energy Engineering (ICAEE).