Cross-Validated Singular Spectrum Analysis for Decomposing and Forecasting Farmers' Terms of Trade in South Sulawesi

Authors

DOI:

https://doi.org/10.30605/proximal.v9i4.10018

Keywords:

Nilai Tukar Petani, Singular Spectrum Analysis, Validasi Silang Rolling-Origin, Dekomposisi Deret Waktu, Sulawesi Selatan

Abstract

Policies such as the timing of rice procurement in South Sulawesi need forecasts of the Farmers' Terms of Trade (NTP) that separate its trend from harvest-related seasonal swings. Singular Spectrum Analysis (SSA) makes this separation without assuming a parametric model or stationarity, but its parameters are usually tuned by trial and error on the data used to report accuracy. We applied trend-only recurrent SSA to the monthly NTP of South Sulawesi (2020–2025, 72 BPS observations), selected its window length and number of components by rolling-origin cross-validation within 2020–2024, and tested it on 2025 against naive, drift, seasonal naive, ETS, and ARIMA benchmarks. The selected model (window length 0.30 times the series length, three trend components) separated a trend that rose steeply in 2023–2024 and turned downward in 2025 from a small seasonal pattern that peaks in February and is lowest in June, information that the naive, drift, and ARIMA forecasts do not provide. Its 2025 MAPE of 2.71% was comparable to the benchmarks (1.37–3.78%), although the naive and drift forecasts were more accurate. Cross-validation also kept the reported accuracy realistic: choosing the parameters on the 2025 data would have reported a MAPE of 1.16% for a setting whose cross-validated MAPE was 33.44%. The NTP is projected to stay above 100 in 2026 (annual mean 117.69). SSA with cross-validated parameters thus offers an interpretable decomposition and competitive forecasts; its parameters should be chosen on training data only, reported with their sensitivity to the validation design, and compared with simple benchmarks.

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, 9(3), 171–176. https://doi.org/10.24843/MTK.2020.v09.i03.p295

Badan Pangan Nasional. (2024). Peraturan Badan Pangan Nasional Nomor 4 Tahun 2024 tentang perubahan atas Peraturan Badan Pangan Nasional Nomor 6 Tahun 2023 tentang harga pembelian pemerintah dan rafaksi harga gabah dan beras. Badan Pangan Nasional.

Badan Pusat Statistik Provinsi Sulawesi Selatan. (2026). Nilai tukar petani Provinsi Sulawesi Selatan, 2020–2025 [Data set]. https://sulsel.bps.go.id

Diebold, F. X., & Mariano, R. S. (1995). Comparing predictive accuracy. Journal of Business & Economic Statistics, 13(3), 253–263. https://doi.org/10.1080/07350015.1995.10524599

Golyandina, N. (2010). On the choice of parameters in singular spectrum analysis and related subspace-based methods. Statistics and Its Interface, 3(3), 259–279. https://doi.org/10.4310/SII.2010.v3.n3.a2

Golyandina, N., & Korobeynikov, A. (2014). Basic singular spectrum analysis and forecasting with R. Computational Statistics & Data Analysis, 71, 934–954. https://doi.org/10.1016/j.csda.2013.04.009

Golyandina, N., Korobeynikov, A., & Zhigljavsky, A. (2018). Singular spectrum analysis with R. Springer. https://doi.org/10.1007/978-3-662-57380-8

Golyandina, N., Nekrutkin, V., & Zhigljavsky, A. (2001). Analysis of time series structure: SSA and related techniques. Chapman & Hall/CRC.

Golyandina, N., & Zhigljavsky, A. (2020). Singular spectrum analysis for time series (2nd ed.). Springer. https://doi.org/10.1007/978-3-662-62436-4

Hamjaya, R. G., Rukmana, D., & Lumoindong, Y. (2022). Analisis faktor-faktor yang mempengaruhi nilai tukar petani tanaman hortikultura di Sulawesi Selatan. Agricore: Jurnal Agribisnis dan Sosial Ekonomi Pertanian Unpad, 7(1), 36–46. https://doi.org/10.24198/agricore.v7i1.39467

Hasan, I. K., & Djakaria, I. (2021). Perbandingan model hybrid ARIMA-NN dan hybrid ARIMA-GARCH untuk peramalan data nilai tukar petani di Provinsi Gorontalo. Jurnal Statistika dan Aplikasinya, 5(2), 155–165. https://doi.org/10.21009/JSA.05204

Hassani, H. (2007). Singular spectrum analysis: Methodology and comparison. Journal of Data Science, 5(2), 239–257. https://doi.org/10.6339/JDS.2007.05(2).396

Hassani, H., Heravi, S., & Zhigljavsky, A. (2009). Forecasting European industrial production with singular spectrum analysis. International Journal of Forecasting, 25(1), 103–118. https://doi.org/10.1016/j.ijforecast.2008.09.007

Hassani, H., Mahmoudvand, R., & Zokaei, M. (2011). Separability and window length in singular spectrum analysis. Comptes Rendus Mathématique, 349(17–18), 987–990. https://doi.org/10.1016/j.crma.2011.07.012

Hyndman, R. J., & Athanasopoulos, G. (2021). Forecasting: Principles and practice (3rd ed.). OTexts. https://otexts.com/fpp3/

Hyndman, R. J., & Khandakar, Y. (2008). Automatic time series forecasting: The forecast package for R. Journal of Statistical Software, 27(3), 1–22. https://doi.org/10.18637/jss.v027.i03

Hyndman, R. J., & Koehler, A. B. (2006). Another look at measures of forecast accuracy. International Journal of Forecasting, 22(4), 679–688. https://doi.org/10.1016/j.ijforecast.2006.03.001

Idrus, R. A., Ruliana, & Aswi. (2022). Penerapan metode singular spectrum analysis dalam peramalan jumlah produksi beras di Kabupaten Gowa. VARIANSI: Journal of Statistics and Its Application on Teaching and Research, 4(2), 49–58. https://doi.org/10.35580/variansiunm40

Istiyanti, D., Widyaningrum, E. N., Nufus, M. R., & Chandrawati, C. (2025). Peramalan harga beras mingguan di Kalimantan Timur menggunakan metode singular spectrum analysis. Jurnal Statistika dan Komputasi, 4(2), 94–105. https://doi.org/10.32665/statkom.v4i2.5662

Khan, M. A. R., & Poskitt, D. S. (2017). Forecasting stochastic processes using singular spectrum analysis: Aspects of the theory and application. International Journal of Forecasting, 33(1), 199–213. https://doi.org/10.1016/j.ijforecast.2016.01.003

R Core Team. (2024). R: A language and environment for statistical computing. R Foundation for Statistical Computing. https://www.R-project.org/

Satriani, S., Nursalam, N., & Ibnas, R. (2020). Peramalan indeks harga konsumen (IHK) di Sulawesi Selatan dengan menggunakan metode singular spectrum analysis (SSA). Jurnal Matematika dan Statistika serta Aplikasinya, 8(1), 82–89. https://doi.org/10.24252/msa.v8i1.17441

Setyaningrum, O. A., Zukhronah, E., & Handajani, S. S. (2023). Peramalan nilai tukar petani (NTP) di Indonesia menggunakan metode hibrida singular spectrum analysis (SSA)–seasonal autoregressive integrated moving average (SARIMA). Prosiding Seminar Nasional Pendidikan Matematika (SENPIKA), 1, 255–266. https://doi.org/10.20527/m7sfd480

Tashman, L. J. (2000). Out-of-sample tests of forecasting accuracy: An analysis and review. International Journal of Forecasting, 16(4), 437–450. https://doi.org/10.1016/S0169-2070(00)00065-0

Widi, M. A. I. N. (2021). Determinan nilai tukar petani perkebunan rakyat di Indonesia. Efficient: Indonesian Journal of Development Economics, 4(1), 1093–1107. https://doi.org/10.15294/efficient.v4i1.40420

Downloads

Published

2026-11-16

How to Cite

Cross-Validated Singular Spectrum Analysis for Decomposing and Forecasting Farmers’ Terms of Trade in South Sulawesi. (2026). Proximal: Jurnal Penelitian Matematika Dan Pendidikan Matematika, 9(4), 1022-1031. https://doi.org/10.30605/proximal.v9i4.10018