THE PERFOMANCE OF THE ARIMAX MODEL ON COOKING OIL PRICE DATA IN INDONESIA

  • Erdanisa Aghnia Ilmani Statistics and Data Science Department, School of Data Science, Mathematics, and Informatics, IPB University, Indonesia https://orcid.org/0009-0007-0972-7248
  • Fida Fariha Amatullah Statistics and Data Science Department, School of Data Science, Mathematics, and Informatics, IPB University, Indonesia https://orcid.org/0009-0005-6140-7458
  • Khairil Anwar Notodiputro Statistics and Data Science Department, School of Data Science, Mathematics, and Informatics, IPB University, Indonesia https://orcid.org/0000-0003-2892-4689
  • Yenni Angraini Statistics and Data Science Department, School of Data Science, Mathematics, and Informatics, IPB University, Indonesia https://orcid.org/0000-0003-3186-2378
  • Laily Nissa Atul Mualifah Statistics and Data Science Department, School of Data Science, Mathematics, and Informatics, IPB University, Indonesia https://orcid.org/0000-0002-5722-8431
Keywords: ARIMAX, Cooking Oil Prices, Forecasting

Abstract

Forecasting is crucial for planning, particularly in addressing potential issues. While ARIMA models are commonly used for time series forecasting, they may need more accuracy by overlooking external factors. The ARIMAX model, which incorporates exogenous variables, is employed to enhance accuracy. This study applies the ARIMAX model to forecast cooking oil prices in Indonesia, known for its complex patterns. Using data from the Directorate General of Domestic Trade and Price Stability (2024), the research highlights fluctuating cooking oil prices from 2010 to 2023 every month. Both ARIMA and ARIMAX models are utilized, with domestic fresh fruit bunch (FFB) prices and the COVID-19 pandemic indicator as exogenous variables. Evaluation based on Mean Absolute Percentage Error (MAPE) shows that the ARIMAX model has a MAPE of 17.31%, compared to 17.69% for the ARIMA model. The lower MAPE value for ARIMAX indicates improved forecasting accuracy by incorporating external factors. Thus, the ARIMAX model is recommended for predicting cooking oil prices, offering better accuracy and valuable insights for policymakers and stakeholders.

 

Downloads

Download data is not yet available.

References

S. Makridakis, S. Wheelwright, and R. Hyndman, “FORECASTING: METHODS AND APPLICATIONS,” in The Journal of the Operational Research Society, vol. 35, 1984.

J. D. Cryer and K.-S. Chan, TIME SERIES ANALYSIS WITH APPLICATIONS IN R, vol. 20, no. 2. 2008.

T. Prasetyo, R. A. Putri, D. Ramdhani, Y. Angraini, and K. A. Notodiputro, “COMPARISON OF THE PERFORMANCE OF THE ARIMA , MULTI-LAYER PERCEPTRON , AND RANDOM FOREST METHODS IN FORECASTING PRECIOUS METAL FUTURES PRICES THAT CONTAIN OUTLIERS,” J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 2, 2024, doi: 10.25126/jtiik.2024117392.

“DATA HARIAN MINYAK GORENG KEMASAN MEI 2023-FEBRUARI 2024.” .

A. A. Hidayat, Mustofa, and A. M. Arlina, “KEBIJAKAN PEMERINTAH DALAM MENGATASI KELANGKAAN MINYAK GORENG PADA MASA PANDEMI COVID-19 DALAM PERSPEKTIF EKONOMI ISLAM,” J. Ekon. dan Bisnis Islam, vol. 10, pp. 20–28, 2023.

N. Sinurat, Z. Alamsyah, and Elwamendri, “DINAMIKA HARGA MINYAK GORENG SAWIT ( MGS ) DAN DAMPAKNYA TERHADAP TERHADAP PERKEBUNAN KELAPA SAWIT INDONESIA,” Sosio Ekon. Bisnis, vol. 19, no. 1, pp. 1–12, 2016.

L. P. Aryanto, M. Adinda, N. Anggreny, and A. R. Lestari, “KEBIJAKAN PEMERINTAH DALAM MENGATASI KELANGKAAN MINYAK GORENG SELAMA PANDEMI COVID-19,” J. Ilm. Pascasarj., vol. 4, no. 1, pp. 27–35, 2024.

W. Adinugroho, “PENDEKATAN CLUSTERING TIME SERIES PADA PERAMALAN HARGA MINYAK GORENG,” J. Ilm. Pop. Median, vol. 4, pp. 47–55, 2021.

N. Halim, S. J. Pririzki, I. Alviari, and D. Y. Dalimunthe, “PREDIKSI HARGA MINYAK GORENG SEBAGAI SUMBER KEBUTUHAN MASYARAKAT DI KOTA PANGKALPINANG,” Semin. Nas. Penelit. dan Pengabdi. pada Masy. 2022, pp. 41–44, 2022.

M. L. S. Putera, “IMPROVISASI MODEL ARIMAX-ANFIS DENGAN VARIASI KALENDER UNTUK PREDIKSI TOTAL TRANSAKSI NON-TUNAI,” Indones. J. Stat. Its Appl., vol. 4, no. 2, pp. 296–310, 2020, doi: 10.29244/ijsa.v4i2.603.

N. Newton, A. Kurnia, and I. M. Sumertajaya, “ANALISIS INFLASI MENGGUNAKAN DATA GOOGLE TRENDS DENGAN MODEL ARIMAX DI DKI JAKARTA,” Indones. J. Stat. Its Appl., vol. 4, no. 3, pp. 545–556, 2020, doi: 10.29244/ijsa.v4i3.694.

A. R. P. Syam, “APPLICATION OF THE AUTOREGRESSIVE INTEGRATED MOVING AVERAGE EXOGENOUS (ARIMAX) WITH CALENDAR VARIATION EFFECT METHOD FOR FORECASTING CHOCOLATE DATA IN INDONESIA AND THE UNITED STATES,” J. Mat. Stat. dan Komputasi, vol. 18, no. 2, pp. 224–236, 2022, doi: 10.20956/j.v18i2.18460.

Elvina Catria, A. A. Putra, D. Permana, and D. Fitria, “ADDING EXOGENOUS VARIABLE IN FORMING ARIMAX MODEL TO PREDICT EXPORT LOAD GOODS IN TANJUNG PRIOK PORT,” UNP J. Stat. Data Sci., vol. 1, no. 1, pp. 31–38, 2023, doi: 10.24036/ujsds/vol1-iss1/10.

W. Hutasuhut H, Amira Anggraeni and R. Tyasnurita, “BAHAN BAKU PLASTIK,” J. Tek. POMITS, vol. 3, no. 2, pp. 169–174, 2014.

R. H. Shumway and D. S. Stoffer, TIME SERIES ANALYSIS AND ITS APPLICATIONS WITH R EXAMPLES, 4th ed. United States of America: Springer International Publishing, 2016.

K. Ameliana and A. Fadilla, “ANALISIS PENGARUH PANIC BUYING DAN HARGA TERHADAP KEPUTUSAN PEMBELIAN MINYAK GORENG PADA MASA PANDEMI COVID-19,” J. Ilm. FEASIBLE, vol. 5, no. 1, pp. 17–27, 2023.

Published
2025-04-01
How to Cite
[1]
E. A. Ilmani, F. F. Amatullah, K. A. Notodiputro, Y. Angraini, and L. N. A. Mualifah, “THE PERFOMANCE OF THE ARIMAX MODEL ON COOKING OIL PRICE DATA IN INDONESIA”, BAREKENG: J. Math. & App., vol. 19, no. 2, pp. 819-828, Apr. 2025.