k-Parameter Approach for False In-Season Anomaly Suppression in Daily Time Series Anomaly Detection
This addresses a specific issue in time series anomaly detection for applications with daily data and weekly patterns, but it is incremental as it builds on existing decomposition methods.
The paper tackles the problem of false positives in daily time series anomaly detection with weekly patterns, specifically 'in-season anomalies' where data points are within their weekly range but off from their weekday position, and proposes a k-parameter approach that provides configurable extra tolerance to suppress misleading alerts while preserving real positives, yielding favorable results.
Detecting anomalies in a daily time series with a weekly pattern is a common task with a wide range of applications. A typical way of performing the task is by using decomposition method. However, the method often generates false positive results where a data point falls within its weekly range but is just off from its weekday position. We refer to this type of anomalies as "in-season anomalies", and propose a k-parameter approach to address the issue. The approach provides configurable extra tolerance for in-season anomalies to suppress misleading alerts while preserving real positives. It yields favorable result.