**Evaluation data**
Evaluation is performed on data from the test subject. Participants will receive the test subect's EEG data, but not the event labels associated with it. These will have to be predicted from the EEG data **using ML models trained on data from the training subjects**. 

```text
    Tip - you'll need to train your models on data from some individuals and apply to data from a new individual that was not part of the training set. Explore different methods to improve your model's ability to transfer to new data. This will be crucial to perform well in the challenge!
```

Like the training data, the evaluation EEG data includes raw EEG signal organized in 30s epochs. Each epoch is associated with a single event marker, which the models will need to predict.

Refer to the [tutorials](https://github.com/BCI-I/BCII-IDUN-Challenge-tutorials) for more details about the evaluation data, metric and submission file.


**Metric**
Given the dataset’s class imbalance, this competition uses the Weighted F1-Score as the primary evaluation metric. The Weighted F1-Score emphasizes the importance of both precision and recall across classes, providing a balanced assessment of model performance, especially on underrepresented classes.

## Submission File
You will need to provide a submission `.csv` file. We've provided detailed instructions on how to prepare this data in the tutorials linked above.  Your submission file should have as many rows as there are epochs in the test dataset. Each row should have an `ID` (the epoch's number in the dataset, starting at 0) and a `TARGET`, a string with the marker's name predicted by your model. 

    ID,Marker
    1,REM
    2,K
    3,A
    etc...