Bayesian Online Changepoint Detection

2007/10/19 by Ryan P. Adams, Ryan Prescott Adams, Adams, Ryan Prescott +3 · 58 citations
Computer Science · Decision Sciences · Mathematics · #Advanced Statistical Process Monitoring #Bayesian Methods and Mixture Models #FOS: Computer and information sciences #Machine Learning (stat.ML) #Statistical Methods and Inference #stat.ML

paper · pdf · doi:10.48550/arxiv.0710.3742

7 pages, 4 figures, latex

arxiv created 2007/10/19 · openalex publication_date 2007/10/19 · arxiv updated 2009/12/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Changepoints are abrupt variations in the generative parameters of a data sequence. Online detection of changepoints is useful in modelling and prediction of time series in application areas such as finance, biometrics, and robotics. While frequentist methods have yielded online filtering and prediction techniques, most Bayesian papers have focused on the retrospective segmentation problem. Here we examine the case where the model parameters before and after the changepoint are independent and we derive an online algorithm for exact inference of the most recent changepoint. We compute the probability distribution of the length of the current ``run,'' or time since the last changepoint, using a simple message-passing algorithm. Our implementation is highly modular so that the algorithm may be applied to a variety of types of data. We illustrate this modularity by demonstrating the algorithm on three different real-world data sets.

Citations

• CONTINUOUS INSPECTION SCHEMES

Cited by

• Observer, Not Player: Simulating Theory of Mind in LLMs through Game Observation
• Large Language Models as Discounted Bayesian Filters
• ARCADE: Adaptive Robot Control with Online Changepoint-Aware Bayesian Dynamics Learning
• TopicProphet: Prophesies on Temporal Topic Trends and Stocks
• Change Point Detection for Functional Autoregressive Processes on the Sphere
• A Quantum Tensor Network-Based Viewpoint for Modeling and Analysis of Time Series Data
• Enhancing Hierarchical Reinforcement Learning through Change Point Detection in Time Series
• Toward Interpretable Evaluation Measures for Time Series Segmentation
• On Multi-entity, Multivariate Quickest Change Point Detection
• Risk-Calibrated Bayesian Streaming Intrusion Detection with SRE-Aligned Decisions
• Inferring Soil Drydown Behaviour with Adaptive Bayesian Online Changepoint Analysis
• A Path Signature Framework for Detecting Creative Fatigue in Digital Advertising
• On Posterior consistency of Bayesian Changepoint models
• Leveraging Multimodal Haptic Sensory Data for Robust Cutting
• When and Whom to Collaborate with in a Changing Environment: A Collaborative Dynamic Bandit Solution
• Graceful Forgetting II. Data as a Process
• Bayesian online collective anomaly and change point detection in fine-grained time series
• Time Series Segmentation through Automatic Feature Learning
• Quantifying and Reducing Bias in Maximum Likelihood Estimation of Structured Anomalies
• Efficacy of Statistical and Artificial Intelligence-based False Information Cyberattack Detection Models for Connected Vehicles
• Sparse Multi-Output Gaussian Processes for Medical Time Series Prediction
• Non-smooth Bayesian Optimization in Tuning Problems
• Bayesian Online Prediction of Change Points
• Robust seasonal cycle of Arctic sea ice area through tipping point in amplitude
• Stein Variational Online Changepoint Detection with Applications to Hawkes Processes and Neural Networks
• Optogenetic manipulation of nuclear Dorsal reveals temporal requirements and consequences for transcription
• Bayesian Changepoint Analysis
• Deep Reinforcement Learning amidst Lifelong Non-Stationarity
• LinXGBoost: Extension of XGBoost to Generalized Local Linear Models
• Empirical Bayesian analysis of simultaneous changepoints in multiple data sequences
• Statistically Valid Post-Deployment Monitoring Should Be Standard for AI-Based Digital Health
• Hierarchical Task Decomposition for Execution Monitoring and Error Recovery: Understanding the Rationale Behind Task Demonstrations
• Online Bayesian Passive-Aggressive Learning
• Powerpropagation: A sparsity inducing weight reparameterisation
• Situationally-Aware Dynamics Learning
• Active Learning for Multiple Change Point Detection in Non-stationary Time Series with Deep Gaussian Processes
• Spatio-temporal Bayesian On-line Changepoint Detection with Model Selection
• Changepoint Analysis of Topic Proportions in Temporal Text Data
• Coincident Learning for Beam-based RF Station Fault Identification Using Phase Information at the SLAC Linac Coherent Light Source
• Towards automated symptoms assessment in mental health
• Selective review of offline change point detection methods
• Rethinking PPG-based Sleep Staging: Datasets, Metrics, and Benchmarks
• Thalamocortical architectures for flexible cognition and efficient learning
• Deep Learning for Multi-Scale Changepoint Detection in Multivariate Time Series
• Quickest change detection with unknown parameters: Constant complexity and near optimality
• A New Pattern Representation Method for Time-Series Data
• Exploring Statistical Change Point Detection Techniques for Performance Anomaly Detection at Mozilla
• Explicit-Duration Markov Switching Models
• Geometric Observables for Financial Regime Detection
• Sequential Bayesian Monitoring for Recoverable and Drifting Processes
• Enhancing Portfolio Optimization with Deep Learning Insights
• A new approach to forecast market interest rates through the CIR model
• Beyond the QBER Threshold: A Temporal QBER Based Machine Learning Framework for Multi Attack Detection in BB84 QKD
• Trend and Variance Adaptive Bayesian Changepoint Analysis & Local Outlier Scoring
• Unsupervised Anomaly Detection in Stream Data with Online Evolving Spiking Neural Networks
• Continual Learning in Practice
• Dynamic time series clustering via volatility change-points
• BLAST: Bayesian online change-point detection with structured image data
• Merging Embedded Topics with Optimal Transport for Online Topic Modeling on Data Streams

Related

• Bayesian Online Prediction of Change Points
• Lagged Exact Bayesian Online Changepoint Detection with Parameter Estimation
• Bayesian Autoregressive Online Change-Point Detection with Time-Varying Parameters
• Robust and Scalable Bayesian Online Changepoint Detection
• A novel changepoint detection algorithm