Teodor Knapik ; Adolphe Ratiarison ; Hasina Razafindralambo
-
An experimental evaluation of choices of SSA forecasting parameters
arima:9641 -
Revue Africaine de Recherche en Informatique et Mathématiques Appliquées,
March 26, 2024,
Volume 40 - 2024
-
https://doi.org/10.46298/arima.9641
An experimental evaluation of choices of SSA forecasting parametersArticle
2 Faculté des Sciences - Université d'Antananarivo
Six time series related to atmospheric phenomena are used as inputs for experiments offorecasting with singular spectrum analysis (SSA). Existing methods for SSA parametersselection are compared throughout their forecasting accuracy relatively to an optimal aposteriori selection and to a naive forecasting methods. The comparison shows that awidespread practice of selecting longer windows leads often to poorer predictions. It alsoconfirms that the choices of the window length and of the grouping are essential. Withthe mean error of rainfall forecasting below 1.5%, SSA appears as a viable alternative forhorizons beyond two weeks.
Keywords: time series forecasting,singular spectrum analysis,parameter selection,[INFO.INFO-CE]Computer Science [cs]/Computational Engineering, Finance, and Science [cs.CE]