AI engineering glossary · Evaluation metrics
What is log loss?
Log loss (also called logarithmic loss, binary cross-entropy): A metric for probabilistic classifiers that averages the negative natural log of the probability assigned to the true class: -(1/N) * sum of ln(p_true). It heavily penalises confident wrong predictions and rewards well-calibrated probabilities. Lower is better, and 0 is perfect.
Log loss: an example
If the true class gets probability 0.9 the loss is -ln(0.9), about 0.105; if it gets 0.1 the loss is about 2.30.
Related terms
More Evaluation metrics terms
- Macro averaging
- Matthews correlation coefficient
- MAUVE
- Max error
- Maximum calibration error
- McNemar's test
- Mean absolute error
- Mean absolute percentage error
Where you learn it
Log loss is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.