On comparing SSA-based change point discovery algorithms

Change point discovery is an important problem in data mining and industrial systems. Different approaches have been proposed and some of the most promising approaches are based on singular spectrum analysis (SSA). These algorithms have the advantages of requiring no ad-hoc tuning for different types of signals and having a built-in noise attenuation mechanism. In this paper we try to unify these approaches and present a novel method for comparing change point discovery algorithms. We then use the proposed method to compare different SSA based change point discovery algorithms. Even though we focused on comparing only SSA based algorithms, the proposed metric applicable to any kind of change point discovery algorithm and have the advantages of requiring no localization steps, and being independent of any predefined thresholds (unlike traditional metrics).