Early Detection of Banking Crises in Indonesia with Adaptive Neuro Fuzzy Inference System

Abstract

Banking crises occurring in a country have a devastating impact on the country's economy and financial system. The threat of the coming banking crisis in Indonesia can be detected by looking at the movement of banking performance indicators such as Total Assets, Bad Debt Ratio, Return on Assets and Loan to Deposit Ratio. So far there is no standard or standard benchmark to indicate the condition of the banking system is in a crisis condition. Therefore it is very necessary to establish an early warning system that can detect a banking crisis in Indonesia so that appropriate policies to deal with disruptions can be taken immediately to prevent the occurrence of the crisis. Many methods are developed to develop a model that can provide such an early warning. Neuro-Fuzzy is one of the most commonly used methods of prediction or diagnosis, with fairly good accuracy. Neuro-Fuzzy is a combination of a Backpropagation Neural Network concept with the fuzzy logic concept. In this study, the authors tried to use the Neuro-Fuzzy method to perform early detection of the banking crisis in Indonesia.