Change point detection in time series data with random forests

Abstract

A large class of monitoring problems can be cast as the detection of a change in the parameters of astatic or dynamic system, based on the effects of these changes on one or more observed variables. Inthis paper, the use of random forest models to detect change points in dynamic systems is considered.The approach is based on the embedding of multivariate time series data associated with normalprocess conditions, followed by the extraction of features from the resulting lagged trajectory matrix.The features are extracted by recasting the data into a binary classification problem, which can besolved with a random forest model. A proximity matrix can be calculated from the model and from thismatrix features can be extracted that represent the trajectory of the system in phase space. The resultsof the study suggest that the random forest approach may afford distinct advantages over a previouslyproposed linear equivalent, particularly when complex nonlinear systems need to be monitored.