Implementation of ARIMAX with Cross-Correlation and Granger Causality Feature Selection for Inflation Forecasting
Implementasi ARIMAX dengan seleksi fitur Cross Correlation dan Granger Causality untuk Prediksi Inflasi
DOI:
https://doi.org/10.33005/santika.v6i1.1098Keywords:
inflasi, ARIMAX, seleksi fitur, Granger Causality, Cross-Correlation FunctionAbstract
Inflasi merupakan indikator makroekonomi penting yang mencerminkan stabilitas harga dalam suatu perekonomian. Peramalan inflasi menjadi krusial dalam mendukung pengambilan kebijakan ekonomi yang tepat. Penelitian ini bertujuan untuk membangun model prediksi inflasi menggunakan pendekatan ARIMAX dengan seleksi fitur berbasis Cross-Correlation Function (CCF) dan uji kausalitas Granger. Data yang digunakan meliputi inflasi serta beberapa variabel makroekonomi seperti suku bunga, nilai tukar, jumlah uang beredar, ekspektasi inflasi, administered price, dan volatile food pada periode 2015–2024. Hasil penelitian menunjukkan bahwa model ARIMAX(0,1,1) merupakan model terbaik dengan nilai AIC dan BIC terendah. Evaluasi model menghasilkan nilai RMSE sebesar 0,053525 dan MAE sebesar 0,040410, yang menunjukkan bahwa model memiliki tingkat kesalahan prediksi yang rendah. Secara keseluruhan, model mampu menangkap pola pergerakan inflasi dengan baik.
References
Mukarramah, M. Zulkarnain, and Arif Ramadhana, “Inflasi Dalam Pertumbuhan Ekonomi: Studi Empiris di Indonesia Periode 1991 – 2024,” vol. 25, Jul. 2025, Accessed: Jan. 24, 2026. [Online]. Available: http://jurnal.umsu.ac.id/index.php/ekawan
S. M. Juhro and B. N. Iyke, “Forecasting Indonesian inflation within an inflation-targeting framework: Do large-scale models pay off?,” Buletin Ekonomi Moneter dan Perbankan/Monetary and banking economics bulletin, vol. 22, no. 4, pp. 423–436, Feb. 2019, doi: 10.21098/bemp.v22i4.1235.
Afrizal, “Analysis of Macroeconomic Variables on the Existence of Inflation in Indonesia Using the Vector Error Correction Model Approach,” Jurnal Ekonomi Kuantitatif Terapan, vol. 17, no. 1, pp. 9–35, Oct. 2025, doi: 10.24843/JEKT.2024.v17.i01.p02.
B. Novianda, “Forecasting Inflation in Indonesia Using ARIMAX : The Role of Money Supply and Exchange Rate,” vol. 13, no. 02, 2025, doi: 10.33019/equity.v13i2.370.
M. Coker, “Short-Term Inflation Forecasting In Sierra Leone: A Comparison of Vector Autoregressive VAR(P), Arimax, And Arima Models,” SSRN Electronic Journal, 2025, doi: 10.2139/ssrn.5278590.
J. Olaniyan, D. Olaniyan, I. C. Obagbuwa, B. M. Esiefarienrhe, A. A. Adebiyi, and O. P. Bernard, “Intelligent Financial Forecasting with Granger Causality and Correlation Analysis Using Bayesian Optimization and Long Short-Term Memory,” Electronics (Basel)., vol. 13, no. 22, p. 4408, Nov. 2024, doi: 10.3390/electronics13224408.
W. W. S. . Wei, Time series analysis : univariate and multivariate methods. Pearson Addison Wesley, 2006.
H. C. Changtzeng, D. F. Chang, and Y. H. Lo, “Detecting concurrent relationships of selected time series data for ARIMAX model,” ICIC Express Letters, Part B: Applications, vol. 10, no. 10, pp. 937–944, Oct. 2019, doi: 10.24507/icicelb.10.10.937.
C. F. Akuma, P. Hewage, T. Bren, C. V. Amaechi, and A. Eche, “Forecasting Nigerian Inflation: A SARIMAX and Granger Causality Analysis of Exchange Rate and Crude Oil Price Impacts,” International Journal of Development Mathematics (IJDM), vol. 2, no. 4, pp. 200–216, Dec. 2025, doi: 10.62054/ijdm/0204.14.
S. Ghosh, S. Mukhoti, and P. Sharma, “Impact of rainfall risk on rice production: realized volatility in mean model,” Apr. 2025.
Y. Si, S. Nadarajah, Z. Zhang, and C. Xu, “Modeling opening price spread of Shanghai Composite Index based on ARIMA-GRU/LSTM hybrid model,” PLoS One, vol. 19, no. 3 March, Mar. 2024, doi: 10.1371/journal.pone.0299164.
D. C. . Montgomery, C. L. . Jennings, and Murat. Kulahci, Introduction to time series analysis and forecasting. Wiley, 2015.
