Prediksi Kurs Rupiah terhadap Dolar dan Yuan Menggunakan LSTM-PSO dan XGBoost
Abstract
The Indonesian rupiah exchange rate is a key determinant of Indonesia's economic conditions and is vulnerable to global geopolitical dynamics, yet geopolitical risk is still rarely incorporated explicitly into exchange rate forecasting models. This study compares the accuracy of XGBoost and Long Short-Term Memory optimized with Particle Swarm Optimization (LSTM-PSO) in forecasting IDR/USD and IDR/CNY, using the Geopolitical Risk Daily (GPRD) index as an external predictor. The dataset comprises daily IDR/USD, IDR/CNY, and GPRD observations from February 2022 to February 2026. The workflow includes data collection, cleaning, and integration, feature engineering, normalization, chronological data splitting, and model evaluation using RMSE, MAE, MAPE, and R². Under the tested scenario, LSTM-PSO yielded lower errors than XGBoost for both currency pairs, with a MAPE below 1% and an R² above 0.89, whereas XGBoost produced a negative R². These findings indicate the potential of LSTM-PSO as an exchange rate forecasting model that incorporates geopolitical risk information, and may serve as a consideration for banks, investors, and international businesses in monitoring exchange rate movements.
Downloads
References
W. Khamidah and R. R. Sugiharti, “Faktor yang Mempengaruhi Nilai Tukar Rupiah terhadap Dollar Amerika, Euro dan Poundsterling,” Ecoplan, vol. 5, no. 1, pp. 40–52, 2022, doi: 10.20527/ecoplan.v5i1.425.
S. D. A. Teja, L. Derick, M. L. Tauryawati, and A. F. Zainuddin, “Prediksi nilai kurs mata uang Dollar Amerika (USD) dan Yuan China (CNY) dengan Rupiah (IDR) menggunakan metode ARIMA prediction,” Var. J. Stat. Its Appl., vol. 6, no. 1, pp. 99–112, 2025, doi: 10.30598/variancevol6iss1page99-112.
M. D. Kurnia and M. Anitasari, “Pengaruh neraca perdagangan barang dan jasa pada nilai tukar rupiah terhadap yuan,” Converg. J. Econ. Perspect., vol. 3, no. 2, pp. 159–178, 2021, doi: 10.33369/convergence-jep.v3i2.22386.
Y. Yudianto, D. Supriyadi, and Kosasih, “Dampak Perselisihan Ukraina-Rusia 2022 Terhadap Perekonomian, Inflasi, Perdagangan Internasional di Asia Tenggara,” COOPETITION J. Ilm. Manaj., vol. 14, no. 2, pp. 293–306, 2023, doi: 10.32670/coopetition.v14i2.3347.
Suherman et al., “Bagaimana Dampak Perang Rusia Ukraina Terhadap Stabilitas Keuangan di Indonesia,” J. Ekon. Manaj. dan Akunt. 3025-1192, vol. 2, no. 4, pp. 288–296, 2024, doi: 10.572349/neraca.v2i4.1281.
I. A. Badhan, “Currency Rate Fluctuations and Their Impact On Supply chain Risk Management: An Empirical Analysis,” Int. J. Bus. Manag. Sci., vol. 04, no. 10, pp. 6–26, 2024, doi: 10.55640/ijbms-04-10-02.
D. C. M. Iacoviello, “Geopolitical Risk Index,” Economic Policy Uncertainty. Accessed: Jun. 28, 2026. [Online]. Available: https://www.policyuncertainty.com/gpr.html
J. R. Francis and R. C. Chia, “Geopolitical Risk ( GPR ) and its Predictability : A Systematic Literature Review,” Int. J. Acad. Res. Bus. Soc. Sci., vol. 13, no. 9, pp. 1082–1099, 2023, doi: 10.6007/IJARBSS/v13-i9/16766.
A. Khaliq, S. Karimi, W. D. Taifur, and E. Ridwan, “Decision SciThe quest for explosive bubbles in the Indonesian Rupiah/US exchange rate: Does the uncertainty trinity matter?ence Letters,” Decis. Sci. Lett., vol. 13, no. 2, pp. 415–426, 2024, doi: 10.5267/dsl.2024.1.005.
I. Hidayat, L. A. Syamsul, I. Akbar, and A. S. Rachman, “Prediksi Nilai Tukar Mata Uang Menggunakan Algoritma Long Short-Term Memory dan Random Forest,” J. Comput. Syst. Informatics, vol. 6, no. 1, pp. 107–116, 2024, doi: 10.47065/josyc.v6i1.6200.
G. S. Mahendra, S. R. Yahya, J. A. Widians, S. Sepriano, A. P. S. Iskandar, and D. Darwin, ARTIFICIAL INTELLIGENCE TOOLS POPULER: Penerapan & Implementasi AI pada Dunia Kerja dan Industri. PT. Sonpedia Publishing Indonesia, 2023.
M. S. Iswahyudi et al., Aplikasi Machine Learning di Berbagai Bidang: Solusi Cerdas Untuk Masa Depan. PT. Sonpedia Publishing Indonesia, 2023.
R. Multiyaningrum, H. R. Dawi, R. Nurhaq, M. Hartanto, and M. Al, “Forecasting the Rupiah exchange rate against the US Dollar using the LSTM algorithm,” Factor M Focus Action Res. Math., vol. 8, no. 2, pp. 201–216, 2025, doi: 10.30762/f_m.v8i2.6530.
I. Talhartit, S. A. Jillali, and M. El Kabbouri, “Enhancing Stock Price Forecasting with LSTM Networks : A Comparative Study of Classic and PSO-Optimized Models on S & P 500 Stock,” Int. J. Econ. Financ., vol. 17, no. 8, pp. 87–94, 2025, doi: 10.5539/ijef.v17n8p87.
X. Zeng, C. Liang, Q. Yang, F. Wang, and J. Cai, “Enhancing stock index prediction : A hybrid LSTM-PSO model for improved forecasting accuracy,” PLoS One, vol. 20, no. 1, pp. 1–31, 2025, doi: 10.1371/journal.pone.0310296.
S. F. N. Islam, A. Sholahuddin, and A. S. Abdullah, “Extreme gradient boosting ( XGBoost ) method in making forecasting application and analysis of USD exchange rates against rupiah Extreme gradient boosting ( XGBoost ) method in making forecasting application and analysis of USD exchange rates against rupi,” J. Phys. Conf. Ser. Pap., vol. 1722, no. 1, pp. 0–11, 2021, doi: 10.1088/1742-6596/1722/1/012016.
Pfahler and J. Felix, “Exchange rate forecasting with advanced machine learning methods Exchange Rate Forecasting with Advanced Machine Learning Methods,” J. Risk Financ. Manag. Provid., vol. 15, no. 1, pp. 1–17, 2022, doi: 10.3390/jrfm15010002.
I. Ullah, Usman Rehman, Dawood Khan, Sulaiman Rashid, Haroon Ullah, “Forecasting Foreign Exchange Rate with Machine Learning Techniques Chinese Yuan to US Dollar Using XGboost and LSTM Model,” iRASD J. Econ., vol. 6, no. 3, pp. 761–775, 2024, doi: 10.52131/joe.2024.0603.0238.
I. F. Amri, N. Yunanita, and F. A. Lestari, “MethodsX Rupiah exchange rate prediction against the US Dollar using a deep neural network with a multi-output sliding window approach,” MethodsX, vol. 15, no. August, p. 103692, 2025, doi: 10.1016/j.mex.2025.103692.
I. F. Amri, N. Yunanita, and F. A. Lestari, “MethodsX Rupiah exchange rate prediction against the US Dollar using a deep neural network with a multi-output sliding window approach,” MethodsX, vol. 15, p. 103692, 2025, doi: 10.1016/j.mex.2025.103692.
Investing.com, “USD/IDR - Historical Data.” Accessed: Jun. 28, 2026. [Online]. Available: https://www.investing.com/currencies/usd-idr-historical-data
Investing.com, “CNY/IDR - Historical Data.” Accessed: Jun. 28, 2026. [Online]. Available: https://id.investing.com/currencies/cny-idr-historical-data
A. Sahrin et al., “Buku Ajar Data Mining,” in 2026.
S. Borrohou, R. Fissoune, and H. Badir, “Data cleaning survey and challenges – improving outlier detection algorithm in machine learning,” J. Smart Cities Soc., vol. 2, no. 3, pp. 125–140, 2023, doi: 10.3233/SCS-230008.
C. Leites, José; Cerqueira, Vitor; Soares, “Lag Selection for Univariate Time Series Forecasting Using Deep Learning: An Empirical Study,” Prog. Artif. Intell. Lect. Notes Comput. Sci., vol. 14969, no. 3, pp. 321–332, 2024, doi: 10.48550/arXiv.2405.11237.
M. Billah, A. Sultana, F. Bhuiyan, and M. G. Kaosar, “Stock price prediction : comparison of different moving average techniques using deep learning model,” Neural Comput. Appl., vol. 36, no. 11, pp. 5861–5871, 2024, doi: 10.1007/s00521-023-09369-0.
K. Yan and Y. Li, “Machine learning-based analysis of volatility quantitative investment strategies for American financial stocks,” Quant. Financ. Econ., vol. 8, no. 11, pp. 364–386, 2024, doi: 10.3934/QFE.2024014.
D. R. Anamisa, F. A. Mufarroha, A. Jauhari, and B. K. Khotimah, “Mathematical Modelling of Engineering Problems Forecasting Ginger Harvest Yields : A Comparative Study of Double Exponential Smoothing and Long Short-Term Memory Models,” Int. Inf. Eng. Technol. Assoc., vol. 11, no. 6, pp. 1481–1490, 2024, doi: 10.18280/mmep.110609.
A. Khansa, A. Prasetya, A. Wida, and D. Rafifah, “Optimalisasi Rekonstruksi Data Hilang untuk Meningkatkan Presisi Prediksi Waktu Salat Berbasis GRU di Wilayah Empat Musim Optimizing Missing Data Reconstruction to Enhance GRU-Based Prayer Time Prediction Precision in Four-Season Regions,” Bul. Sist. Inf. dan Teknol. Islam, vol. 7, no. 2, pp. 116–127, 2026, doi: 10.33096/busiti.v7i2.3458.
H. Hewamalage, K. Ackermann, and C. Bergmeir, “Forecast evaluation for data scientists : common pitfalls and best practices,” Data Min. Knowl. Discov., vol. 37, no. 2, pp. 788–832, 2023, doi: 10.1007/s10618-022-00894-5.
R. Sari and W. Kurniadi, “Penerapan Metode Machine Learning ( Random Forest & XGBoost ) untuk Memprediksi Prestasi Akademik Berdasarkan Faktor Internal dan Eksternal Siswa Application of Machine Learning Methods ( Random Forest & XGBoost ) to Predict Academic Achievement Based on,” Bul. Sist. Inf. dan Teknol. Islam, vol. 6, no. 4, pp. 205–213, 2025, doi: 10.33096/busiti.v6i4.3205.
M. Jahron, J. A. Widians, and A. Tejawati, “Multivariate LSTM With the RSI-14 Technical Indicator for Stock Price Forecasting,” TEPIAN, vol. 7, no. 3, pp. 270–279, 2026, doi: 10.51967/tepian.v7i3.3919.
H. Xiao, “Enhanced separation of long-term memory from short-term memory on top of LSTM : Neural network-based stock,” PLoS One, vol. 20, no. 6, pp. 1–34, 2025, doi: 10.1371/journal.pone.0322737.
M. M. Mundu, “Comparative Analysis of Model Evaluation Metrics in Energy Systems , Environmental Modeling , and Sustainability Science,” Int. J. Energy Res., vol. 6, pp. 1–13, 2026, doi: 10.1155/er/6170467.
V. Kumar, N. Kedam, K. V. Sharma, and D. J. Mehta, “Advanced Machine Learning Techniques to Improve Hydrological Prediction : A Comparative Analysis of Streamflow Prediction Models,” MDPI, vol. 15, no. 14, p. 2572, 2023, doi: 10.3390/w15142572.
Copyright (c) 2026 Oktaria Indi Cahyani, Joan Angelina Widians, Fahrul Agus
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
