R-squared in Watson OpenScale quality metrics
The R-squared is the ratio of the total variance and the explained variance in Watson OpenScale. R-squared measures how well the regression predictions approximate the actual values. The higher the R-squared score, the better the model fits to the actual values.
R-squared at a glance
- Description: Ratio of difference between target variance and variance for prediction error to target variance
- 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: Regression
- Chart values: Last value in the timeframe
- Metrics details available: None
Do the math
The R-squared metric is defined in the following formula.
explained variation
R-squared = _____________________
total variation
Learn more
Parent topic: Quality metrics overview