TY - JOUR

T1 - Intelligent Identification of Trend Components in Singular Spectrum Analysis

AU - Golyandina, Nina

AU - Dudnik, Pavel

AU - Shlemov, Alex

PY - 2023/7/24

Y1 - 2023/7/24

N2 - Singular spectrum analysis (SSA) is a non-parametric adaptive technique used for time series analysis. It allows solving various problems related to time series without the need to define a model. In this study, we focus on the problem of trend extraction. To extract trends using SSA, a grouping of elementary components is required. However, automating this process is challenging due to the nonparametric nature of SSA. Although there are some known approaches to automated grouping in SSA, they do not work well when the signal components are mixed. In this paper, a novel approach that combines automated identification of trend components with separability improvement is proposed. We also consider a new method called EOSSA for separability improvement, along with other known methods. The automated modifications are numerically compared and applied to real-life time series. The proposed approach demonstrated its advantage in extracting trends when dealing with mixed signal components. The separability-improving method EOSSA proved to be the most accurate when the signal rank is properly detected or slightly exceeded. The automated SSA was very successfully applied to US Unemployment data to separate an annual trend from seasonal effects. The proposed approach has shown its capability to automatically extract trends without the need to determine their parametric form.

AB - Singular spectrum analysis (SSA) is a non-parametric adaptive technique used for time series analysis. It allows solving various problems related to time series without the need to define a model. In this study, we focus on the problem of trend extraction. To extract trends using SSA, a grouping of elementary components is required. However, automating this process is challenging due to the nonparametric nature of SSA. Although there are some known approaches to automated grouping in SSA, they do not work well when the signal components are mixed. In this paper, a novel approach that combines automated identification of trend components with separability improvement is proposed. We also consider a new method called EOSSA for separability improvement, along with other known methods. The automated modifications are numerically compared and applied to real-life time series. The proposed approach demonstrated its advantage in extracting trends when dealing with mixed signal components. The separability-improving method EOSSA proved to be the most accurate when the signal rank is properly detected or slightly exceeded. The automated SSA was very successfully applied to US Unemployment data to separate an annual trend from seasonal effects. The proposed approach has shown its capability to automatically extract trends without the need to determine their parametric form.

KW - automated SSA

KW - seasonality

KW - singular spectrum analysis

KW - time series decomposition

KW - trend extraction

UR - https://www.mendeley.com/catalogue/1a25d055-ae63-30c9-aa84-10f62a38d8ed/

U2 - 10.3390/a16070353

DO - 10.3390/a16070353

M3 - Article

VL - 16

JO - Algorithms

JF - Algorithms

SN - 1999-4893

IS - 7

M1 - 353

ER -