Enhancing Inflation Forecasting in Indonesia Using N-BEATSx with Exogenous Factors
DOI:
https://doi.org/10.30871/jaic.v10i3.12759Keywords:
Deep Learning, Exogenous, Forecasting, Inflation, N-BEATSxAbstract
Accurate inflation forecasting is crucial for economic stability and effective policymaking, particularly in emerging economies such as Indonesia, where monetary policy, global commodity markets, exchange rate fluctuations, and recurring religious seasonal events simultaneously influence price dynamics. This study proposes an inflation forecasting framework using the N-BEATSx (Neural Basis Expansion Analysis for Time Series with Exogenous Variables) deep learning model, incorporating macroeconomic variables, global oil prices, BI Rate, and the USD/IDR exchange rate, alongside Ramadan and Eid al-Fitr calendar dummy variables as exogenous inputs. The dataset comprises 153 monthly observations spanning January 2013 to September 2025, split into training, validation, and test sets, with a forecasting horizon of six months. The N-BEATSx model is benchmarked against SARIMAX, LSTM, and Prophet. Results on the test set show that N-BEATSx achieves competitive performance (RMSE 0.0067, MAE 0.0058, SMAPE 51.77%) outperforming SARIMAX (RMSE 0.0297, MAE 0.0266) and LSTM (RMSE 0.0098, MAE 0.0084). Although Prophet yields marginally lower absolute errors, the MAE gap is minimal (0.0002), while N-BEATSx offers superior interpretability through an explicit decomposition of forecasts into trend, seasonality, and exogenous components. Component decomposition analysis reveals that macroeconomic exogenous variables dominate the forecast output, confirming their theoretical relevance as inflation drivers. Six-month-ahead forecasts project inflation in the range of 2.47% - 3.54% for October 2025 to March 2026, approaching Bank Indonesia’s upper target corridor, suggesting the need for preemptive monetary policy measures.
Downloads
References
[1] A. N. Paradhita, “Prediksi Inflasi di Indonesia Menggunakan Algoritma Fuzzy dengan Bahasa Pemrograman Phyton,” Jurnal Penelitian Inovatif, vol. 4, no. 2, pp. 457–464, Apr. 2024, doi: 10.54082/jupin.339.
[2] N. Hadi, S. Alam, and I. Kurniawan, “Penerapan Model Lstm (Long Short-Term Memory) Dalam Peramalan Inflasi Month On Month Di Indonesia,” JATI (Jurnal Mahasiswa Teknik Informatika), vol. 9, no. 5, pp. 9009–9015, Jul. 2025, doi: 10.36040/jati.v9i5.15119.
[3] S. J. Taylor and B. Letham, “Forecasting at scale,” Sep. 27, 2017. doi: 10.7287/peerj.preprints.3190v2.
[4] S. Saleh, D. T. K. Wardani, and M. A. Ivantri, “Ramadan, Eid Ul Fitr, And Inflation: Lesson From Indonesian Subnational Data,” Jurnal Ekonomi & Studi Pembangunan, vol. 20, no. 2, 2019, doi: 10.18196/jesp.20.2.5020.
[5] Badan Pusat Statistik, “Inflasi Year-On-Year (y-o-y),” 2025. Accessed: Sep. 20, 2025. [Online]. Available: https://www.bps.go.id/id/pressrelease?page=1&keyword=inflasi&year=2025
[6] A. Nurfarhana and T. Anita, “Pengaruh BI Rate dan Nilai Tukar Mengambang oleh Bank Indonesia terhadap Tingkat Inflasi di Indonesia Tahun 2008–2015,” Sosio e-kons, vol. 9, no. 3, pp. 194–199, Mar. 2018, doi: 10.30998/sosioekons.v9i3.2248.
[7] R. Wulan, N. Nurpadilah, and R. Pebrian, “Pengaruh Inflasi, Harga Minyak Dunia, Dan Suku Bunga (Bi Rate) Terhadap Indeks Harga Saham Gabungan (Ihsg) (Data Per Bulan Periode 2011-2020)”, PMB, vol. 1, no. 2, pp. 130–143, Feb. 2023.
[8] S. P. Sari and S. Nurjannah, “Analisis Pengaruh Nilai Tukar, Jumlah Uang Beredar dan BI Rate Terhadap Inflasi di Indonesia dan Dampaknya Terhadap Daya Beli Masyarakat,” AKTIVA: Journal of Accountancy and Management, vol. 1, no. 1, pp. 21–29, Jan. 2023, doi: 10.24260/aktiva.v1i1.1015.
[9] A. Yusnitasari, “Forecasting Indonesian Inflation Using The Box-Jenkins Arima Method,” Jurnal Paradigma Multidisipliner (JPM), vol. 1, no. 2, pp. 152–159, 2020.
[10] M. I. Rizki and T. A. Taqiyyuddin, “Penerapan Model SARIMA untuk Memprediksi Tingkat Inflasi di Indonesia,” Jurnal Sains Matematika dan Statistika, vol. 7, no. 2, Aug. 2021, doi: 10.24014/jsms.v7i2.13168.
[11] A. Mutiara, N. Fitriyati, and Mahmudi, “Analisis Laju Prediksi Inflasi Di Indonesia: Perbandingan Model Garch/Arch Dengan Long Short Term Memory,” Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistika, vol. 4, no. 1, pp. 94–112, 2023.
[12] M. Kristanaya, A. T. Darmaliana, and S. S. M. Wara, “Implementation of the Stacked LSTM Model in Predicting Inflation in Indonesia Based on the USD/IDR Exchange Rate,” Disover - Data Science, Informatics, Statistics, & Electrical Research Conference (2025), vol. 1, no. 1, pp. 1–8, 2025.
[13] M. N. Riswanda, T. Trimono, and W. S. J. Saputra, “Prediksi Laju Inflasi di Jawa Timur Menggunakan Model N-BEATS dan Optimasi Optuna,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 5, no. 3, Jul. 2025, doi: 10.57152/malcom.v5i3.2141.
[14] B. Indonesia, “BI Rate.” Accessed: Sep. 19, 2025. [Online]. Available: https://www.bi.go.id/en/statistik/indikator/BI-Rate.aspx
[15] “Data Historis Minyak Mentah WTI Berjangka,” Investing.com. Accessed: Sep. 20, 2025. [Online]. Available: https://id.investing.com/commodities/crude-oil-historical-data
[16] M. Kristanaya, A. T. Darmaliana, and S. S. M. Wara, “Implementation of the Stacked LSTM Model in Predicting Inflation in Indonesia Based on the USD/IDR Exchange Rate,” Discover - Data Science, Informatics, Statistics, & Electrical Research Conference (2025), vol. 1, no. 1, pp. 1–8, 2025.
[17] M. Heru Widiyanto, R. Mayasari, and G. Garno, “Implementasi Time Series Pada Data Penjualan Di Gaikindo Menggunakan Algoritma Seasonal Arima,” JATI (Jurnal Mahasiswa Teknik Informatika), vol. 7, no. 3, pp. 1501–1506, Oct. 2023, doi: 10.36040/jati.v7i3.6879.
[18] Kaka Kalam Djati Permana, Esa Firmansyah, and Beben Sutara, “Analisis Komparatif Linear Regression dan Support Vector Regression pada Prediksi Penduduk Kabupaten Sumedang,” Data Sciences Indonesia (DSI), vol. 5, no. 2, pp. 84–92, Dec. 2025, doi: 10.47709/dsi.v5i2.7423.
[19] R. H. Nindy, H. Iftiah, A. Waladi, and Y. Perdana, “Implementation of Machine Learning for Stock Price Prediction Using the LSTM Algorithm,” MISTIC: Media Applied Science and Engineering, vol. 1, no. 2, pp. 31–37, 2025.
[20] K. G. Olivares, C. Challu, G. Marcjasz, R. Weron, and A. Dubrawski, “Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx,” Int J Forecast, vol. 39, no. 2, pp. 884–900, Apr. 2023, doi: 10.1016/j.ijforecast.2022.03.001.
[21] Y. Shangguan et al., “Transfer Learning-Enhanced N-BEATSx for Multivariate Forecasting of Tight Gas Well Production,” Electronics (Basel), vol. 14, no. 19, p. 3875, Sep. 2025, doi: 10.3390/electronics14193875.
[22] A. Handijono and Z. Suhatman, “Penerapan Machine Learning untuk Mempertahankan Loyalitas Pelanggan menggunakan Churn Prediction”, Spectrum, vol. 2, no. 3, pp. 259–266, Jul. 2025.
[23] H. J. Weerts, A. C. Mueller, and J. Vanschoren, “Importance of tuning hyperparameters of machine learning algorithms,” arXiv preprint arXiv:2007.07588, 2020. doi: 10.48550/arXiv.2007.07588.
[24] M. S. Alfa, A. Ibrahim, and M. I. Umar, “The Comparison of Various Exponential Smoothing Models and Their Significance in ModernTime Series Forecasting,” Afropolitan Journals, vol. 8, no. 1, pp. 8–17, 2022.
[25] M. A. Fawaid, R. A. Pramunendar, N. A. Sri Winarsih, M. S. Rohman, and D. O. Ratmana, “Optimasi Model U-Net Backbone Resnet50 Pada Segmentasi Citra Banjir Menggunakan Sequential Hyperparameter Tuning”, rabit, vol. 11, no. 1, pp. 1478–1488, Jan. 2026.
[26] Prapas, I., Derakhshan, B., Mahdiraji, A.R. et al. Continuous Training and Deployment of Deep Learning Models. Datenbank Spektrum 21, 203–212 (2021). https://doi.org/10.1007/s13222-021-00386-8
[27] M. A. Akmal, Trimono, and A. R. Pratama, “Penerapan LSTM untuk Prediksi Jangka Pendek Penjualan Paket Data (Studi Kasus: Kota Malang),” Discover - Data Science, Informatics, Statistics, & Electrical Research Conference (2025), vol. 1, no. 1, pp. 19–27, 2025.
[28] N. Mehdiyev, D. Enke, P. Fettke, and P. Loos, “Evaluating Forecasting Methods by Considering Different Accuracy Measures,” Procedia Comput Sci, vol. 95, pp. 264–271, 2016, doi: 10.1016/j.procs.2016.09.332
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Talitha Adilla Fujisai Panglima Putri, Mohammad Idhom, Muhammad Nasrudin
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
