A new approach to modeling early warning systems for currency crises: Can a machine-learning fuzzy expert system predict the currency crises effectively?

Abstract

This paper presents a hybrid causal model for predicting the occurrence of currency crises by using the neuro fuzzy modeling approach. The model integrates the learning ability of the neural network with the inference mechanism of fuzzy logic. The empirical results show that the proposed neuro fuzzy model leads to a better prediction of crisis. Significantly, the model can also construct a reliable causal relationship among the variables through the obtained knowledge base. Compared to neural network and the traditionally used techniques such as logit, the proposed model can thus lead to a somewhat more prescriptive modeling approach based on determinate causal mechanisms towards finding ways to prevent currency crises.