There seems to be no single country that can escape from currency crises. This paper aims to answer: (i) How to determine exchange market pressure (EMP)? and (ii) To what extent the contribution of selected indicators to the prediction of currency crises?. The study adopts indicators developed by Kaminski, et.al (1999) by using signal extraction method as the early warning system (EWS) mechanism. By employing four selected variables, International reserve, real exchange rates, credit growth, and domestic inflation, the findings suggest the periods of crises fluctuated over the observations under various thresholds. The EMP touched the Kaminsky's line only during the Asian and global financial crises. Meanwhile, the Garcia's, Park's and Lestano's line was passed through frequently over the observations, and it implies that the financial system was cyclically under shocks. In conclusion, the currency crises frequently appear attacking Indonesia's financial system so that need to be mitigated by net open position (NOP) as macroprudential instrument.
Partial Discharge Signal Extraction Method Based on EDSSV and Low Rank RBF Neural Network
