APLIKASI MODEL ARIMA GARCH DALAM PERAMALAN DATA NILAI TUKAR RUPIAH TERHADAP DOLAR TAHUN 2017-2022

Nickyta Shavira Maharani (Program Studi Statistika dan Sains Data, IPB University, Indonesia)
Yenni Angraini (IPB University)
Mahesa Ahmad Rahmawan (Program Studi Statistika dan Sains Data, IPB University, Indonesia)
Oktaviani Aisyah Putri (Program Studi Statistika dan Sains Data, IPB University, Indonesia)
Steven Kurniawan (Program Studi Statistika dan Sains Data, IPB University, Indonesia)
Tias Amalia Safitri (Program Studi Statistika dan Sains Data, IPB University, Indonesia)
Akbar Rizki (Program Studi Statistika dan Sains Data, IPB University, Indonesia)
Wiwik Andriyani Lestari Ningsih (Program Studi Statistika dan Sains Data, IPB University, Indonesia)
Nabila Ghoni Trisno Hidayatulloh (Program Studi Statistika dan Sains Data, IPB University, Indonesia)
Andika Putri Ratnasari (Program Studi Statistika dan Sains Data, IPB University, Indonesia)

Jurnal Matematika Sains dan Teknologi
Vol. 24 No. 1 (2023)

The Indonesian rupiah (IDR) exchange rate is used to gauge Indonesia's economic stability. Maintaining the IDR exchange rate's stability is critical since it has a direct impact on Indonesia's national monetary situation, particularly during the Covid-19 pandemic. Forecasting the rupiah exchange rate is important to do and is one way to assess government policy. The data series to be used here are IDR exchange rate from the Yahoo Finance. It consists of 271 data taken from August 2017 to October 2022. This study aims to use the Autoregressive Integrated Moving Average (ARIMA) and Generalized Autoregressive Conditional Heteroscedasticity (GARCH) modeling method using the R-studio software and predict the IDR exchange rate. The ARIMA method describes the data based on a certain time series. ARCH-Lagrange Multiplier (ARCH-LM) was applied on the residuals of the best ARIMA model to test whetoer the data is heteroscedasticity. The testing result shows that the residual of the IDR exchange rate is heteroscedasticity. Therefore, the GARCH model can be used to handle it. The results of this study are obtained for the ARIMA(2,1,3) GARCH(3,6) model as the best and describe the actual data pattern with a mean absolute percentage error (MAPE) forecasting value is 1,99%.