A Reliable Framework for Human-in-the-Loop Anomaly Detection in Time Series

arXiv:2405.03234v1 Announce Type: cross
Abstract: Time series anomaly detection is a critical machine learning task for numerous applications, such as finance, healthcare, and industrial systems. However, even high-performed models may exhibit potential issues such as biases, leading to unreliable outcomes and misplaced confidence. While model explanation techniques, particularly visual explanations, offer valuable insights to detect such issues by elucidating model attributions of their decision, many limitations still exist -- They are primarily instance-based and not scalable across dataset, and they …

abstract anomaly anomaly detection applications arxiv biases confidence cs.hc cs.lg detection finance framework healthcare however human industrial loop machine machine learning series systems time series type visual while