A time series is a series of observations of a variable that is collected, recorded, or observed over a period of time in sequence. Singular Spectrum Analysis is a powerful method to analyze time series data by decomposing the original time series data into several small components that can be identified, such as trend, periodic, and noise components. One of the datasets that can be used is data on the number of train passengers in Sumatera in 2013–2022. In this study, the Singular Spectrum Analysis method is used to forecast the number of train passengers in Sumatera in 2013–2022. The best Singular Spectrum Analysis model in this study was obtained at a window length of 22 and a number of groups of 8, with a MAPE value of 19.55%.
Copyrights © 2023