## Metric

The metric for the evaluation of this competition is the [Area Under Curve (AUC)](https://en.wikipedia.org/wiki/Receiver_operating_characteristic). Participants will calculate and submit anomaly scores for each test sample instead of a decision result. Here, the anomaly score takes a large value when the input signal seems to be anomalous, and vice versa.

## Submission Format

You should submit a single .csv file reporting the results of your model. The file (in CSV format, with header row as the *sample_submission.csv*) contains anomaly scores for each audio file in the test data of the evaluation dataset. Result items can be in any order. All rows must be the following format: 

```

[filename (string)],[anomaly score (real value)]

```

You can download an example submission file (sample_submission.csv) on the [Data page](https://www.kaggle.com/competitions/eurecom-aml-2022-challenge-2/data).