PREDIKSI NILAI TUKAR MATA UANG IDR TERHADAP USD DENGAN TEKNIK DEEP LEARNING MENGGUNAKAN MODEL RECURRENT NEURAL NETWORK

Abstract

Exchange currency rate becomes one of the most important things on country economic growth. In Indonesia,
the rate has affected seriously to economic growth and political stability. Government needs to have some actions in
order to stabilize the rate. Knowing the pattern of exchange rate against the IDR to USD is a mandatory by government
for determining future policies or as consideration in future decision-making. Therefore, government needs an analysis
tool for forecasting the rate. In this study, the authors aim to predict the pattern of exchange rate using deep learning
method with sequence-to-sequence recurrent neural network (seq2seq RNN) model utilizing a varied selection of inputs
types. The result showed that the seq2seq model has an accuracy to predict sequence data series of exchange rate over
ARIMA method as a comparison result.