Unravel Anomalies: An End-to-end Seasonal-Trend Decomposition Approach for Time Series Anomaly Detection

TL;DR

This paper presents TADNet, an end-to-end model that uses seasonal-trend decomposition to improve anomaly detection in complex time-series data, achieving state-of-the-art results.

Contribution

Introduction of TADNet, a novel end-to-end framework that links anomalies to specific decomposition components for better detection accuracy.

Findings

TADNet outperforms existing methods on real-world datasets.

Pre-training on synthetic data enhances detection performance.

Decomposition components help interpret anomaly types.

Abstract

Traditional Time-series Anomaly Detection (TAD) methods often struggle with the composite nature of complex time-series data and a diverse array of anomalies. We introduce TADNet, an end-to-end TAD model that leverages Seasonal-Trend Decomposition to link various types of anomalies to specific decomposition components, thereby simplifying the analysis of complex time-series and enhancing detection performance. Our training methodology, which includes pre-training on a synthetic dataset followed by fine-tuning, strikes a balance between effective decomposition and precise anomaly detection. Experimental validation on real-world datasets confirms TADNet's state-of-the-art performance across a diverse range of anomalies.