Artificial Neural Network for Predicting Indonesian Economic Growth Using Macroeconomics Indicators

The economic crisis could take place all over again. It can be prevented and overcome by forecasting economic conditions. The common way to forecast economic conditions is to measure economic growth using inflation-adjusted Gross Domestic Product (GDP) or real GDP. Economic growth gives information about how well the economy performed. Prediction using Artificial Neural Network (ANN) is commonly used. ANN is a computational system inspired by the works of a human brain. The difference between ANN and other computational method is that ANN can solve highly complex and nonlinear problems. Interest in using ANN for forecasting has led to a tremendous surge in research activities in the past decade. ANN provides great prediction result and better accuracy compared to other methods for non-linear variable relations. This research purpose is to predict the Indonesian economic growth by using macroeconomic variables as a good reflection of the economic condition. Prediction with ANN has 95.81% of forecast accuracy and 4.19% of forecast error with the best ANN configuration using 2N+1 formula. Based on accuracy, the ANN method using macroeconomic indicators such as consumption, investment, government expenditure, gross export and gross import is the best way to forecast economic growth.