2021/06/11 by Deokwoo Jung, Jung, Deokwoo, Nandini Ramanan +10 · 1 citation
Computer Science · Engineering · Mathematics · #Anomaly (physics) #Anomaly Detection Techniques and Applications #Anomaly detection #Artificial intelligence #Benchmark (surveying) #Bootstrapping (finance) #Bottleneck #Computer science #Data mining #Data set #Engineering #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine learning #Mathematics #Metric (unit) #Model selection #Network Security and Intrusion Detection #Parametric statistics #Series (stratigraphy) #Statistics #Time Series Analysis and Forecasting #Time series #cs.LG
paper · pdf · doi:10.48550/arxiv.2106.07473
published in arXiv (Cornell University) (Cornell University) · 11 pages, 1 Figure, 4 tables
arxiv created 2021/06/11 · openalex publication_date 2021/06/11 · arxiv updated 2021/06/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Anomaly detection for time-series data becomes an essential task for many data-driven applications fueled with an abundance of data and out-of-the-box machine-learning algorithms. In many real-world settings, developing a reliable anomaly model is highly challenging due to insufficient anomaly labels and the prohibitively expensive cost of obtaining anomaly examples. It imposes a significant bottleneck to evaluate model quality for model selection and parameter tuning reliably. As a result, many existing anomaly detection algorithms fail to show their promised performance after deployment. In this paper, we propose LaF-AD, a novel anomaly detection algorithm with label-free model selection for unlabeled times-series data. Our proposed algorithm performs a fully unsupervised ensemble learning across a large number of candidate parametric models. We develop a model variance metric that quantifies the sensitivity of anomaly probability with a bootstrapping method. Then it makes a collective decision for anomaly events by model learners using the model variance. Our algorithm is easily parallelizable, more robust for ill-conditioned and seasonal data, and highly scalable for a large number of anomaly models. We evaluate our algorithm against other state-of-the-art methods on a synthetic domain and a benchmark public data set.