Possibility for Proactive Anomaly Detection
This addresses the limitation of existing models that rely on error between output and ground truth, making them impractical for real-world applications to reduce damages or losses, though it appears incremental as it builds on forecasting and data-driven methods.
The paper tackles the problem of time-series anomaly detection by proposing a proactive approach that establishes anomaly thresholds from training data and detects anomalies when predicted values exceed these thresholds, achieving evaluation on four benchmarks with analysis of predictable and unpredictable anomalies.
Time-series anomaly detection, which detects errors and failures in a workflow, is one of the most important topics in real-world applications. The purpose of time-series anomaly detection is to reduce potential damages or losses. However, existing anomaly detection models detect anomalies through the error between the model output and the ground truth (observed) value, which makes them impractical. In this work, we present a \textit{proactive} approach for time-series anomaly detection based on a time-series forecasting model specialized for anomaly detection and a data-driven anomaly detection model. Our proactive approach establishes an anomaly threshold from training data with a data-driven anomaly detection model, and anomalies are subsequently detected by identifying predicted values that exceed the anomaly threshold. In addition, we extensively evaluated the model using four anomaly detection benchmarks and analyzed both predictable and unpredictable anomalies. We attached the source code as supplementary material.