2020/11/07 by Miguel de Carvalho, de Carvalho, Miguel, Gabriel Martos +1
Computer Science · Engineering · Mathematics · #Algorithm #Applications (stat.AP) #Applied mathematics #Computer science #Control Systems and Identification #Extension (predicate logic) #FOS: Computer and information sciences #Interval (graph theory) #Machine learning #Mathematics #Methodology (stat.ME) #Neural Networks and Applications #Series (stratigraphy) #Singular spectrum analysis #Singular value decomposition #Statistical and numerical algorithms #Symbolic data analysis #Symbolic dynamics #Theoretical computer science #Time series #stat.AP #stat.ME
paper · pdf · doi:10.48550/arxiv.2011.03872
openalex publication_date 2020/11/07 · arxiv created 2020/11/08 · arxiv updated 2020/11/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
In this article we propose an extension of singular spectrum analysis for\ninterval-valued time series. The proposed methods can be used to decompose and\nforecast the dynamics governing a set-valued stochastic process. The resulting\ncomponents on which the interval time series is decomposed can be understood as\ninterval trendlines, cycles, or noise. Forecasting can be conducted through a\nlinear recurrent method, and we devised generalizations of the decomposition\nmethod for the multivariate setting. The performance of the proposed methods is\nshowcased in a simulation study. We apply the proposed methods so to track the\ndynamics governing the Argentina Stock Market (MERVAL) in real time, in a case\nstudy that covers the most recent period of turbulence that led to discussions\nof the government of Argentina with the International Monetary Fund.\n