PERBANDINGAN PROPHET, XGBOOST, MLP UNTUK PREDIKSI KURS USD KE IDR
Article Sidebar
Read Counter : 18
Download : 10
Main Article Content
Abstract
Peramalan kurs USD/IDR yang akurat sangat krusial bagi stabilitas ekonomi Indonesia. Penelitian ini bertujuan untuk mengevaluasi dan membandingkan kinerja tiga model machine learning, yaitu Prophet, XGBoost, dan Multi-Layer Perceptron (MLP) dalam memprediksi kurs tengah harian USD/IDR. Metode penelitian yang digunakan adalah analisis kuantitatif komparatif pada data historis JISDOR dari Oktober 2019 hingga Oktober 2025. Model Prophet diterapkan sebagai pendekatan time series murni, sedangkan XGBoost dan MLP diuji menggunakan transformasi supervised learning dengan rekayasa fitur (fitur lag, rolling statistics, dan kalender). Kinerja model dievaluasi menggunakan metrik MAE dan RMSE pada dua skema pembagian data (80:20 dan 70:30). Hasil penelitian menunjukkan bahwa XGBoost secara signifikan mengungguli model lainnya, terutama pada skema 80:20, dengan mencapai MAE terendah (Rp100,60), MAPE (0,62%), dan R² positif (0,8603). Sebaliknya, Prophet dan MLP dengan konfigurasi dasar gagal menangkap volatilitas data dan menghasilkan R² negatif. Temuan ini mengindikasikan bahwa pendekatan supervised learning dengan rekayasa fitur, khususnya menggunakan XGBoost, lebih efektif untuk memprediksi kurs USD/IDR jangka pendek.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This work is licensed under a Jurnal Komunikasi Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
References
[1] H. H. Alwi and L. Nirawati, “Pengaruh Inflasi, Suku Bunga Bank Indonesia, dan Nilai Tukar Rupiah (USD/IDR) terhadap Indeks Saham Bisnis-27 di Bursa Efek Indonesia (BEI),” Al-Kharaj : Jurnal Ekonomi, Keuangan & Bisnis Syariah, vol. 5, no. 2, pp. 620–635, Aug. 2022, doi: 10.47467/alkharaj.v5i2.1242.
[2] W. Khamidah and R. Sugiharti, “Faktor yang Mempengaruhi Nilai Tukar Rupiah Terhadap Dolar Amerika, Euro dan Poundsterling,” Ecoplan, vol. 5, no. 1, pp. 40–52, Apr. 2022, doi: 10.20527/ecoplan.v5i1.425.
[3] A. Wiejaya and I. Fenriana, “Prediksi Harga Saham Top 10 NASDAQ dengan Time Series Prophet,” bit-Tech, vol. 7, no. 2, pp. 252–262, Dec. 2024, doi: 10.32877/bt.v7i2.1736.
[4] R. S. Santoso and F. K. Sari Dewi, “Konfigurasi Model Prophet Untuk Prediksi Harga Saham Sektor Teknologi di Indonesia Yang Akurat,” Jurnal Buana Informatika, vol. 15, no. 01, pp. 50–58, Apr. 2024, doi: 10.24002/jbi.v15i1.8634.
[5] Y. Zhang, “Stock Price Prediction Method Based on XGboost Algorithm,” 2023, pp. 595–603. doi: 10.2991/978-94-6463-030-5_60.
[6] K. H. Suradiradja, “Algoritme Machine Learning Multi-Layer Perceptron dan Recurrent Neural Network untuk Prediksi Harga Cabai Merah Besar di Kota Tangerang,” Faktor Exacta, vol. 14, no. 4, p. 194, Jan. 2022, doi: 10.30998/faktorexacta.v14i4.10376.
[7] P. B. Guruge and Y. H. P. P. Priyadarshana, “Time series forecasting-based Kubernetes autoscaling using Facebook Prophet and Long Short-Term Memory,” Front Comput Sci, vol. 7, Feb. 2025, doi: 10.3389/fcomp.2025.1509165.
[8] T. Verdonck, B. Baesens, M. Óskarsdóttir, and S. vanden Broucke, “Special issue on feature engineering editorial,” Mach Learn, vol. 113, no. 7, pp. 3917–3928, Jul. 2024, doi: 10.1007/s10994-021-06042-2.
[9] Y. A. Prasetyo, E. Utami, and A. Yaqin, “Pengaruh Komposisi Split Data Terhadap Performa Akurasi Analisis Sentimen Algoritma Naïve Bayes dan SVM,” Journal of Electrical Engineering and Computer (JEECOM), vol. 6, no. 2, pp. 382–390, Oct. 2024, doi: 10.33650/jeecom.v6i2.9188.
[10] C. B. Aditya Satrio, W. Darmawan, B. U. Nadia, and N. Hanafiah, “Time series analysis and forecasting of coronavirus disease in Indonesia using ARIMA model and PROPHET,” Procedia Comput Sci, vol. 179, pp. 524–532, 2021, doi: 10.1016/j.procs.2021.01.036.
[11] S. L. Sheeba, N. Gupta, R. M. A. Ragavender, and D. Divya, “Time series model for stock market prediction utilising prophet,” Turkish Journal of Computer and Mathematics Education, vol. 12, no. 6, pp. 4529–4534, 2021.
[12] X. Guan et al., “Construction of the XGBoost model for early lung cancer prediction based on metabolic indices,” BMC Med Inform Decis Mak, vol. 23, no. 1, p. 107, Jun. 2023, doi: 10.1186/s12911-023-02171-x.
[13] I. Hanif, “Implementing Extreme Gradient Boosting (XGBoost) Classifier to Improve Customer Churn Prediction,” in Proceedings of the Proceedings of the 1st International Conference on Statistics and Analytics, ICSA 2019, 2-3 August 2019, Bogor, Indonesia, EAI, 2020. doi: 10.4108/eai.2-8-2019.2290338.
[14] B. Ma, G. Yan, B. Chai, and X. Hou, “XGBLC: an improved survival prediction model based on XGBoost,” Bioinformatics, vol. 38, no. 2, pp. 410–418, Jan. 2022, doi: 10.1093/bioinformatics/btab675.
[15] A. Ostovar, D. D. Davari, and M. Dzikuć, “Determinants of Design with Multilayer Perceptron Neural Networks: A Comparison with Logistic Regression,” Sustainability, vol. 17, no. 6, p. 2611, Mar. 2025, doi: 10.3390/su17062611.
[16] A. Sumayli, “Development of advanced machine learning models for optimization of methyl ester biofuel production from papaya oil: Gaussian process regression (GPR), multilayer perceptron (MLP), and K-nearest neighbor (KNN) regression models,” Arabian Journal of Chemistry, vol. 16, no. 7, p. 104833, Jul. 2023, doi: 10.1016/j.arabjc.2023.104833.
[17] S. Nosratabadi, S. Ardabili, Z. Lakner, C. Mako, and A. Mosavi, “Prediction of Food Production Using Machine Learning Algorithms of Multilayer Perceptron and ANFIS,” Agriculture, vol. 11, no. 5, p. 408, May 2021, doi: 10.3390/agriculture11050408.
[18] A. D. Sidik and A. Ansawarman, “Prediksi Jumlah Kendaraan Bermotor Menggunakan Machine Learning,” Formosa Journal of Multidisciplinary Research, vol. 1, no. 3, pp. 559–568, Jul. 2022, doi: 10.55927/fjmr.v1i3.745.
[19] M. Muharrom, “Analisis Komparasi Algoritma Data Mining Naive Bayes, K-Nearest Neighbors dan Regresi Linier Dalam Prediksi Harga Emas,” Bulletin of Information Technology (BIT), vol. 4, no. 4, pp. 430–438, Dec. 2023, doi: 10.47065/bit.v4i4.986.
[20] D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput Sci, vol. 7, p. e623, Jul. 2021, doi: 10.7717/peerj-cs.623.
[21] A. N. Maharadja, I. Maulana, and B. A. Dermawan, “Penerapan Metode Regresi Linear Berganda untuk Prediksi Kerugian Negara Berdasarkan Kasus Tindak Pidana Korupsi,” Journal of Applied Informatics and Computing, vol. 5, no. 1, pp. 95–102, Jul. 2021, doi: 10.30871/jaic.v5i1.3184.
[22] M. R. Athallah and A. F. Rozi, “Implementasi Data Mining Untuk Prediksi Peramalan Penjualan Produk Hj Karpet Menggunakan Metode Linear Regression,” Jurnal Sains dan Teknologi (JSIT), vol. 2, no. 3, pp. 180–187, Feb. 2023, doi: 10.47233/jsit.v2i3.550.
[23] S. D. Puspa, J. Riyono, and F. Puspitasari, “Analisis Faktor-Faktor yang Mempengaruhi Pemahaman Konsep Matematis Mahasiswa dalam Pembelajaran Jarak Jauh Pada Masa Pandemi Covid-19,” Jurnal Cendekia : Jurnal Pendidikan Matematika, vol. 5, no. 1, pp. 302–320, Mar. 2021, doi: 10.31004/cendekia.v5i1.533.