PERAMALAN NILAI TUKAR PETANI (NTP) DI INDONESIA MENGGUNAKAN METODE HIBRIDA SINGULAR SPECTRUM ANALYSIS (SSA)-SEASONAL AUTOREGRESSIVE INTEGRATED MOVING AVERAGE (SARIMA)
DOI:
https://doi.org/10.20527/m7sfd480Keywords:
NTP, hibrida, SSA, SARIMA, peramalan, runtun waktuAbstract
Kemajuan sektor pertanian suatu negara dapat dilihat dari kesejahteraan petaninya. Nilai Tukar Petani (NTP) dapat dijadikan indikator dari kesejahteraan petani. NTP merupakan rasio antara indeks harga yang diterima petani (Id) dan indeks harga yang dibayarkan petani (Ib) sehingga diharapkan dari waktu ke waktu nilainya terus mengalami kenaikan. NTP dapat digunakan sebagai bahan pertimbangan dalam penentuan kebijakan untuk mengembangkan sektor pertanian di Indonesia. Oleh karena itu, diperlukan peramalan NTP. Penelitian ini bertujuan untuk meramalkan NTP di Indonesia menggunakan metode hibrida Singular Spectrum Analysis (SSA) - Seasonal Autoregressive Integrated Moving Average (SARIMA). Data yang digunakan adalah data NTP dari bulan Januari 2008 hingga Desember 2022 di Indonesia. Metode yang digunakan yaitu hibrida SSA-SARIMA. SSA mendekomposisikan data NTP kedalam komponen tren dan noise. SARIMA digunakan untuk memodelkan komponen noise. Peramalan metode hibrida SSA-SARIMA didapatkan dengan menjumlahkan hasil peramalan SSA dan hasil peramalan komponen noise model SARIMA. Hasil penelitian menunjukkan bahwa metode hibrida SSA dengan window length sebesar 84 dan model SARIMA didapatkan nilai MAPE sebesar 1,429%. Metode hibrida SSA-SARIMA dapat meramalkan NTP dengan baik. Hasil peramalan NTP pada periode Januari – Maret 2023 berturut-turut yaitu 110,477; 110,132; dan 109,936 yang artinya petani sejahtera karena nilai NTP lebih dari 100.
The progress of a country's agricultural sector can be seen from the welfare of its farmers. Farmers' Terms of Trade (FTT) can be used as an indicator of farmer welfare. FTT is the ratio between the price index received by farmers (Id) and the price index paid by farmers (Ib) so it is expected that from time to time its value will continue to increase. FTT can be used as material for consideration in determining policies to develop the agricultural sector in Indonesia. Therefore, it is necessary to forecast FTT. This study aims to predict FTT in Indonesia using the Singular Spectrum Analysis (SSA) - Seasonal Autoregressive Integrated Moving Average (SARIMA) hybrid method. The data used is FTT data from January 2008 to December 2022 in Indonesia. The method used is SSA-SARIMA hybrid. SSA decomposes NTP data into trend and noise components. SARIMA is used to model the noise component. Forecasting of the SSA-SARIMA hybrid method is obtained by summing the results of the forecasting of the SSA and the forecasting results of the noise component of the SARIMA model. The results showed that the SSA hybrid method with a window length of 84 and the SARIMA model obtained a MAPE value of 1.429%. The SSA-SARIMA hybrid method can predict FTT well. The FTT forecasting results for the January – March 2023 period are 110,477; 110,132; and 109,936, which means farmers are prosperous because the FTT value is more than 100.
Downloads
References
Andhika, G. B., Sumarjaya, I. W., & Srinadi, I. G. A. M., (2020). Peramalan Nilai Tukar Petani Menggunakan Metode Singular Spectrum Analysis. E-Jurnal Matematika. 7, 171-176.
Arumsari, M., & Dani, A. T. R. (2021). Peramalan data runtun waktu menggunakan model hybrid time series regression–autoregressive integrated moving average. Jurnal Siger Matematika, 2, 1-12.
Aziz, R. A., & Sulistijanti, W. (2018). Peramalan Kunjungan Wisatawan Mancanegara Melalui Bandara Adi Sucipto Menggunakan Support Vector Machine. Prosiding University Research Colloquium, 131-138.
Badan Pusat Statistik. (2022). Nilai Tukar Petani. Diakses di https://www.bps.go.id .
Basari, M. S. N., & Achmad, A. I. (2021). Metode Singular Spectrum Analysis untuk Meramalkan Indeks Harga Konsumen Indonesia Tahun 2019. Prosiding Statistika, 484-491.
Darmawan, G., Rosadi, D., & Ruchjana, B. N. (2022). Hybrid Model of Singular Spectrum Analysis and ARIMA for Seasonal Time Series Data. CAUCHY-Jurnal Matematika Murni dan Aplikasi, 7, 302-315.
Fajar, M. (2020). Perbandingan Kinerja Peramalan Pertumbuhan Ekonomi Indonesia dengan ARIMA, SSA dan Hybrid ARIMA-SSA. Diakses di https://www.researchgate.net/profile/Muhammad-Fajar/publication/333531309_Perbandingan_Kinerja_Peramalan_Pertumbuhan_Ekonomi_Indonesia_dengan_ARIMA_SSA_dan_Hybrid_ARIMA-SSA/links/5cf211b8299bf1fb184e8ee5/Perbandingan-Kinerja-Peramalan-Pertumbuhan-Ekonomi-Indonesia-dengan-ARIMA-SSA-dan-Hybrid-ARIMA-SSA.pdf
Golyandina, N. & Korobeynikov, A. (2013). Basic Singular Spectrum Analysis and Forecasting with R. Computational Statistics dan Data Analysis,1-40.
Golyandina, N., Nekrutkin, V., & Zhigljavsky, A.A. (2001). Analysis of Time Series Structure: SSA and Related Techniques. Chapman dan Hall/CRC.
Golyandina, N., Zhigljavsky, (2020). Singular Spectrum Analysis for time series. Cardiff: Springer.
Hassani, Hossein. (2007). Singular Spectrum Analysis: Methodology and Comparison. Journal of Data Science , 5, 239-257.
Hassani, H., & Thomakos, D. (2010). A review on singular spectrum analysis for economic and financial time series. Statistics and its Interface, 3, 377-397.
Suratha, I. K. (2015). Krisis petani berdampak pada ketahanan pangan di Indonesia. Media Komunikasi Geografi, 16, 67-80.
Waeto, S., Chuarkham, K., & Intarasit, A. (2017). Research Article Forecasting Time Series Movement Direction with Hybrid Methodology. Hindawi Journal of Probability and Statistics, 1-8.
Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159-175.
Zhang, Q., Wang, B. D., He, B., Peng, Y., & Ren, M. L. (2011). Singular spectrum analysis and ARIMA hybrid model for annual runoff forecasting. Water resources management, 25, 2683-2703.
Downloads
Published
Issue
Section
License
Copyright (c) 2023 SENPIKA
This work is licensed under a Creative Commons Attribution 4.0 International License.
