LLM-Augmented Changepoint Detection: A Framework for Ensemble Detection and Automated Explanation
This addresses the need for more accurate and interpretable changepoint detection for analysts and decision-makers in domains like finance and environmental science, though it is incremental as it builds on existing ensemble and LLM techniques.
The paper tackles the problem of suboptimal changepoint detection and lack of interpretability in time series analysis by introducing an ensemble method that combines ten algorithms and an LLM-powered explanation pipeline, achieving superior performance and automated contextual narratives.
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.