In order to focus on reliable detection with an emphasis on low false-alarm rate, submissions are evaluated on the weighted AUC. To calculate the weighted AUC, each region of the ROC curve is weighted according to these chosen parameters:
```
tpr_thresholds = [0.0, 0.4, 1.0]
weights = [2, 1]
```
In other words, the area between the true positive rate of 0 and 0.4 is weighted 2X, the area between 0.4 and 1 is now weighed (1X). The total area is normalized by the sum of weights such that the final weighted AUC is between 0 and 1.

The figure below illustrates the different areas. This example also shows that the submission #2 has the lowest AUC but is ranked first since it outperforms its competitors for low False Positive Rate (FPR). On the opposite, the submission #3 has the highest AUC but would have been ranked third.

![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F1951250%2Ff250ff6a4e04bac332fa14d539ed813e%2FKaggle.png?generation=1588207999884987&alt=media)


## Submission File
For each `Id` (image) in the test set, you must provide a score that indicates how likely this image contains hidden data: the higher the score, the more it is assumed that image contains secret data. The file should contain a header and have the following format:

    Id,Label
    0001.jpg,0.1
    0002.jpg,0.99
    0003.jpg,1.2
    0004.jpg,-2.2
    etc.