Application of Artificial Neural Network to Predict Short-Term Capital Flow

The last decade witnessed a significant increase in net private capital inflows in China. Some of them are short-term capital flows, which are typically considered to be highly volatile. For effectively forecasting the short-term capital flows, a three-layered neural feedforward network was employed in this paper. In light of the weakness of the conventional Back-Propagation algorithm, 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 prediction of short-term capital flow.

I. Introduction

The last decade witnessed an increased frequency of crises in emerging economies, which indicated that great risks associated with capital flows. Capital inflows, while accelerating the economy growth and reducing the volatility of consumption, tend to pose a serious challenges for macroeconomy management. In particular, the short-term capital flow is typically considered to be highly volatile. High shares of short-term capital flow can, therefore, expose countries to the risk of sudden stop or abrupt reversal of capital flows. Sudden reversal of capital inflows may increase the vulnerability of countries to financial crises as happened in Asian crises in 1997–1998 [1].