Logarithmic loss at a glance

Copy link to section

• Description: Mean of logarithms target class probabilities (confidence). It is also known as Expected log-likelihood.
• Default thresholds: Lower limit = 80%
• Default recommendation:
  • Upward trend: An upward trend indicates that the metric is deteriorating. Feedback data is becoming significantly different than the training data.
  • Downward trend: A downward trend indicates that the metric is improving. This means that model retraining is effective.
  • Erratic or irregular variation: An erratic or irregular variation indicates that t The feedback data is not consistent between evaluations. Increase the minimum sample size for the Quality monitor.
• Problem type: Binary classification and multiclass classification
• Chart values: Last value in the timeframe
• Metrics details available: None

Do the math

Copy link to section

For a binary model, Logarithmic loss is calculated by using the following formula:

-(y log(p) + (1-y)log(1-p))
Copy to clipboardCopied to clipboard

Where p = true label and y = predicted probability

For a multi-class model, Logarithmic loss is calculated by using the following formula:

  M
-SUM Yo,c log(Po,c)
 c=1 
Copy to clipboardCopied to clipboard

Where M > 2, p = true label, and y = predicted probability

Learn more

Copy link to section

Reviewing quality results

Parent topic: Quality metrics overview