Open Challenges in Time Series Anomaly Detection: An Industry Perspective
It highlights gaps in anomaly detection for industry applications, but is incremental as it reviews existing challenges without proposing new solutions.
The paper identifies that current time-series anomaly detection research overlooks practical industry needs, such as streaming algorithms and human-in-the-loop scenarios, based on an investigation of cloud systems, and calls for new research and benchmarks.
Current research in time-series anomaly detection is using definitions that miss critical aspects of how anomaly detection is commonly used in practice. We list several areas that are of practical relevance and that we believe are either under-investigated or missing entirely from the current discourse. Based on an investigation of systems deployed in a cloud environment, we motivate the areas of streaming algorithms, human-in-the-loop scenarios, point processes, conditional anomalies and populations analysis of time series. This paper serves as a motivation and call for action, including opportunities for theoretical and applied research, as well as for building new dataset and benchmarks.