7th ISF

MATH015 - Nonparametric Bayesian Online Change Point Detection Using Kernel Density Estimation with Nonparametric Hazard Function

This paper aims to develop Bayesian online change point detection (BOCD), a parametric change point detection method, into a nonparametric method to be able to detect change points in a free-distribution time series. Instead of using predefined exponential family distribution for predictive probability, we use kernel density estimation in which two possible options have been proposed. The first is manual constant bandwidth selection. This option provides a fast computation of KDE as it can pursue dynamic programming. Another option for maximum accuracy is a nonparametric bandwidth estimator. Additionally, to pursue the goal of fully nonparametric change point detection, the predefined hazard function in BOCD method is changed to be a nonparametric estimator. The performance of the proposed method was intensively evaluated with simulated and real-life data and compared with other traditional methods. It was found that nonparametric BOCD gives a better solution in general cases as a consequence of the adaptive property of KDE. But this also comes with a drawback: it requires a sufficient amount of data to form a precise distribution curve to accurately detect change points

Show More