Predicting risks of capital flow using artificial neural network and Levenberg Marquardt algorithm

Under the opening economic circumstances, forecasting the risks of capital flow has special significance. For effectively early warning the risks associated with capital flow, a new evaluation index system of risks was created on the basis of thirteen influencing variables. Then a three-layered neural feedforward network was employed to predict the risks of capital flow. The Levenberg-Marquardt algorithm was used to train the neural network. The simulation results indicate that the predictive model can be used to carry out the early warning of capital flow risks.