Binary log loss by forecast
Find the average log penalty and detect impossible forecasts for observed outcomes.
Your entries stay in this page’s memory and are not submitted to us. Downloads are generated locally. Reloading or leaving the page clears your entries. Do not enter patient information.
The starting values are hypothetical. Use aggregate or synthetic inputs only.
Calculation results
- Mean log loss
- 0.46209812
- Impossible observed outcomes
- 0
- Total
- 3
How to interpret the output
Use the probability of the event, identical for everyone in a row. Natural logarithms give loss in nats. A probability of zero assigned to an observed outcome gives infinite loss. No clipping is applied.
Method reference