Singular spectrum analysis (SSA) is a relatively new and powerful nonparametric method for analyzing time series that is an alternative to the classic methods. This methodology has proved to provide an efficient analysis of time series in various disciplines as the assumptions of stationarity and Gaussian residuals can be relaxed. The Era of Big Data has brought very long and complex time series. Although SSA have provided advantages over traditional methods, the computational time needed for the analysis of long time series might make it unappropriated. We propose the randomized SSA which intends to be an alternative to SSA for long time series without losing the quality of the analysis. The SSA and the randomized SSA are compared in terms of quality of the analysis and computational time, using Monte Carlo simulations and real data.
