Prediction system of economic crisis in Indonesia using time series analysis and system dynamic optimized by genetic algorithm

Abstract

Economic crisis that had happened at 1997-1998 in Indonesia has stimulated researchers to study it further by utilizing economic indicators. The economic indicators, GDP (Gross Domestic Product) and inflation per year from 1980-2011, will be tested using time series analysis and system dynamic optimized by genetic algorithm. This research have applied system dynamic in order to get characteristic value of prediction economic crisis in Indonesia with various conditions besides genetic algorithm (GA) is used to help the dynamic system in finding a coefficient of data historic optimization. The methods prior to predict consist of two phases, i.e. training and testing. The result shows 93%-99% accuracy for training and up to 90% for testing. It concludes that the prediction system is able to fit data in finding historical optimal without avoid error.