LLM-Augmented Changepoint Detection: A Framework for Ensemble Detection and Automated Explanation

TL;DR

This paper presents a new framework that combines ensemble statistical methods with Large Language Models to improve changepoint detection accuracy and provide automated, contextual explanations for regime changes in time series data.

Contribution

It introduces an ensemble detection approach with ten algorithms and an LLM-powered explanation pipeline, enhancing robustness and interpretability over existing methods.

Findings

Achieves higher detection accuracy than individual methods

Provides automated, contextual explanations for detected changepoints

Demonstrates utility across multiple domains like finance and environmental science

Abstract

This paper introduces a novel changepoint detection framework that combines ensemble statistical methods with Large Language Models (LLMs) to enhance both detection accuracy and the interpretability of regime changes in time series data. Two critical limitations in the field are addressed. First, individual detection methods exhibit complementary strengths and weaknesses depending on data characteristics, making method selection non-trivial and prone to suboptimal results. Second, automated, contextual explanations for detected changes are largely absent. The proposed ensemble method aggregates results from ten distinct changepoint detection algorithms, achieving superior performance and robustness compared to individual methods. Additionally, an LLM-powered explanation pipeline automatically generates contextual narratives, linking detected changepoints to potential real-world historical events. For private or domain-specific data, a Retrieval-Augmented Generation (RAG) solution enables explanations grounded in user-provided documents. The open source Python framework demonstrates practical utility in diverse domains, including finance, political science, and environmental science, transforming raw statistical output into actionable insights for analysts and decision-makers.