New recommendation to predict export value using big data and machine learning technique

Official statistics on monthly export values have a publicity lag between the current period and published publication. None of previous researchers estimated value exports for period. This circumstance is due to limitations in obtaining supporting data that can predict criteria goods. AIS one type big provide solutions producing latest indicators forecast values. Statistical Methods Conventional Machine Learning are implemented as forecasting methods. Seasonal ARIMA Artificial Neural Network (ANN) methods both used research Indonesia’s exports. However, ANN has weakness requires high computational costs obtain optimal parameters. Genetic Algorithm (GA) effective increasing accuracy. Based these backgrounds, this paper aims develop select an indicator Indonesia optimize performance by combining algorithm with genetic (GA-ANN). The successfully established five be predictors model. According model evaluation results, succeeded improving indicated resulting RMSE GA-ANN value, which smaller than