Sudden stops of capital flows to emerging markets: A new prediction approach

In this paper, we propose a new prediction approach for forecasting sudden stop events of capital flows to emerging countries. The new approach is to combine conventional approaches (signal extraction and statistical regression approaches) to maintain their advantages. We apply the new approach as well as conventional approaches to actual data and conduct prediction performance comparisons. The empirical results show that the new approach significantly improves prediction ability. The new approach is proven to have some potential merit as an alternative approach to improving prediction ability and can also be applied to various types of financial crisis events.