Area under ROC in Watson OpenScale quality metrics
Area under receiver-operating characteristic curve (ROC) gives the area under recall and false positive rate curve in Watson OpenScale. It calculates the sensitivity against the fallout rate.
Area under ROC at a glance
- Description: Area under recall and false positive rate curve
- Default thresholds: Lower limit = 80%
- Default recommendation:
- Upward trend: An upward trend indicates that the metric is improving. This means that model retraining is effective.
- Downward trend: A downward trend indicates that the metric is deteriorating. Feedback data is becoming significantly different than the training data.
- Erratic or irregular variation: An erratic or irregular variation indicates that the feedback data is not consistent between evaluations. Increase the minimum sample size for the Quality monitor.
- Problem type: Binary classification
- Chart values: Last value in the timeframe
- Metrics details available: Confusion matrix
Do the math
The Area under ROC is plotted parametrically as the True positive rate versus the False positive rate withe respect to a threshold T.
Learn more
Parent topic: Quality metrics overview