Change-Point Detection in Time-Series Data by Relative Density-Ratio Estimation

TL;DR

This paper introduces a new change-point detection method for time-series data using relative density-ratio estimation, which is effective and efficient across various real-world applications.

Contribution

The paper proposes a novel non-parametric change-point detection algorithm based on relative Pearson divergence and direct density-ratio estimation.

Findings

Effective detection in artificial datasets

Successful application to real-world data

Demonstrates efficiency and accuracy

Abstract

The objective of change-point detection is to discover abrupt property changes lying behind time-series data. In this paper, we present a novel statistical change-point detection algorithm based on non-parametric divergence estimation between time-series samples from two retrospective segments. Our method uses the relative Pearson divergence as a divergence measure, and it is accurately and efficiently estimated by a method of direct density-ratio estimation. Through experiments on artificial and real-world datasets including human-activity sensing, speech, and Twitter messages, we demonstrate the usefulness of the proposed method.