A water-treatment plant has a long turbidity trace and a few odd spikes, but no labeled incident rows. Staff want those spikes flagged. Which SageMaker algorithm fits?
Select an answer to reveal the explanation.
Short Explanation
Think of a long turbidity trace with odd spikes and no labeled incidents. Staff want those spikes flagged. Random Cut Forest. Inventing fake incident labels for XGBoost is the trap.
Full Explanation
SageMaker Random Cut Forest detects anomalies on an unlabeled trace. Inventing incident labels for XGBoost is the trap. DeepAR forecasts related series. Translate does not flag turbidity spikes.