## Evaluation

Submissions are evaluated on [Average Precision](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.average_precision_score.html). Average Precision calculates average precision of all prediction scores at different thresholds. This metric produces a value between 0 and 1 where a value closer to 1 indicates that your model can accurately detect all past phishing scammer EOAs without mislabelling too many benign EOAs as phishing scammers. 

## Submission File Format

The file should contain a header and have the following format:
```
Id,Predicted
42,0.99
43,0.25
44,0.53
....
```
You can download an example submission file (sample_submission.csv) on the [Data page](http://www.kaggle.com/competitions/forta/data).