Pier-attendance hosts sit at 20 percent CPU with clean 200s, so the on-call treats the system as healthy. Ticket-office outcomes have drifted for a month. Official 4.1 knowledge includes ML Lens monitoring principles. What is missing?
Select an answer to reveal the explanation.
Short Explanation
Hosts sit at 20 percent CPU with clean 200s, but ticket-office outcomes drifted for a month. Watch the model and the data, not only hosts. Host utilization alone is not model health, and an instance-family pick is Domain 3.
Full Explanation
The Machine Learning Lens monitoring idea is to capture data, compare to a baseline, detect data, model, bias, or attribution issues, and alert. Host utilization alone is not model health. Rekognition and an instance-family pick are not that lens.