Position Paper: Quo Vadis, Unsupervised Time Series Anomaly Detection?

arXiv:2405.02678v1 Announce Type: new
Abstract: The current state of machine learning scholarship in Timeseries Anomaly Detection (TAD) is plagued by the persistent use of flawed evaluation metrics, inconsistent benchmarking practices, and a lack of proper justification for the choices made in novel deep learning-based model designs. Our paper presents a critical analysis of the status quo in TAD, revealing the misleading track of current research and highlighting problematic methods, and evaluation practices. Our position advocates for a shift in focus …

abstract anomaly anomaly detection arxiv benchmarking cs.ai cs.cv cs.lg current deep learning designs detection evaluation evaluation metrics machine machine learning metrics novel paper practices series state time series timeseries type unsupervised