collaborators

6 papers

stat.ME2026

When lookout sees crackle: Anomaly detection via kernel density estimation

Rob J Hyndman, Sevvandi Kandanaarachchi, Katharine Turner

We present an updated version of lookout -- an algorithm for detecting anomalies using kernel density estimates with bandwidth based on Rips death diameters -- with theoretical gua…

stat.ME2026

Anomaly detection using surprisals

Rob J Hyndman, David T. Frazier

Anomaly detection methods are widely used but often rely on ad hoc rules or strong assumptions, and they often focus on tail events, missing ``inlier'' anomalies that occur in low-…

stat.ME2026

Online conformal inference for multi-step time series forecasting

Xiaoqian Wang, Rob J Hyndman

We consider the problem of constructing distribution-free prediction intervals for multi-step time series forecasting, with a focus on the temporal dependencies inherent in multi-s…

cs.HC2025

ggtime: A Grammar of Temporal Graphics

Cynthia A. Huang, Mitchell O'Hara-Wild, Rob J. Hyndman +1

Visualizing changes over time is fundamental to learning from the past and anticipating the future. However, temporal semantics can be complicated, and existing visualization tools…

stat.OT2025

Good intentions, unintended consequences: exploring forecasting harms

Bahman Rostami-Tabar, Travis Greene, Galit Shmueli +1

Organizations worldwide that rely on data-driven approaches regularly employ forecasting methods to enhance their planning and decision-making processes. While extensive research h…

cs.LG2025

Extreme Value Modelling of Feature Residuals for Anomaly Detection in Dynamic Graphs

Sevvandi Kandanaarachchi, Conrad Sanderson, Rob J. Hyndman

Detecting anomalies in a temporal sequence of graphs can be applied is areas such as the detection of accidents in transport networks and cyber attacks in computer networks. Existi…