Peramalan Indeks Harga Konsumen dengan Metode Singular Spectral Analysis (SSA) dan Seasonal Autoregressive Integrated Moving Average (SARIMA)

Main Authors: Lubis, Deltha Airuzsh, Johra, Muhamad Budiman Johra, Darmawan, Gumgum Darmawan
Other Authors: Departemen Statistika FMIPA UNPAD
Format: Article info application/pdf Journal
Bahasa: eng
Terbitan: Matematika UIN Sunan Ampel Surabaya , 2017
Subjects:
CPI
Online Access: http://mantik.uinsby.ac.id/index.php/Mantik1/article/view/54
http://mantik.uinsby.ac.id/index.php/Mantik1/article/view/54/pdf
Daftar Isi:
  • Consumer Price Index (CPI) are the indicators used to measure the inflation and deflation of a group of goods and services in general. Forecasting CPI to be important as early detection in facing price hikes. This study uses the SSA and SARIMA. SARIMA a parametric model that requires various assumptions while SSA is a nonparametric technique that is free from a variety of assumptions, but both methods require seasonal patterns in the data. Based on the research results, methods of SSA with length window(L) of 24 and a grouping of 4 (1 group of seasonal and 3 groups of trends) and SARIMA models of order (0,1,1), (0,1,1) 6 is the most accurate and reliable models in forecasting CPI to the value Padang Sidempuan City. Forecasting CPI Padangsidimpuan City for the next 5 months with SSA method and SARIMA (0,1,1), (0,1,1) 6 shows the pattern of a trend is likely to increase but forecasting the 5th month with SSA method showed a surge in the value of CPI high or high inflation will occur.