From statistical process control and operations research, descended from the control charts Walter A. Shewhart drew at Bell Labs (1924; Economic Control of Quality of Manufactured Product, 1931), and surveyed for modern data by Varun Chandola, Arindam Banerjee, and Vipin Kumar (Anomaly Detection: A Survey, 2009).
Makes three choices explicit for any watched measure, the normal baseline, the threshold for different enough, and who acts when it fires, producing early warning of real shifts.
When to reach for it
When a metric, control, or process has a normal range and a shift beyond the noise needs to be caught early.
How it runs
- Define the signal and how often it is sampled.
- Build and document a baseline of normal behavior.
- Set a threshold matched to the cost of misses and false alarms.
- Name who responds and what they do.
- Label each alert, and update the baseline and threshold.
- Revalidate the baseline on a fixed cadence.
Where it sits in SOLVE eX
Go to the source
- Control chart memorandum, Bell Laboratories, 1924
- Economic Control of Quality of Manufactured Product, 1931
- Anomaly Detection: A Survey, ACM Computing Surveys, 2009