The evaluation metric for this competition is a multinomial [Log-Loss](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.log_loss.html). The log-loss measure the quality of the predicted probabilities. Check out our[ blog post ](https://medium.com/geekculture/football-prediction-performance-how-to-calculate-hit-ratio-and-log-loss-1e5e22310497)if you want to know more about it.

### Submission file

**For every match in the dataset**, submission files should contain four columns: `id`,  `home`, `draw`, and `away`. The columns home stands for the probability of the Home team to win the match, the column away for the Away team to win, and the columns draw for the probability of a Draw. Each column expects a double between 0 and 1, and the sum of the three probabilities to be equals one. The `id` column contains the id of the predicted match.

### Submission Format

The file should contain a header **in the correct order** and have the following format:
```
id,home,away,draw
1,0.3,0.5,0.2
2,0.45,0.25,0.3
...
```