Submissions will be evaluated using the R² ([coefficient of determination](https://en.wikipedia.org/wiki/Coefficient_of_determination)) metric, which measures how well the predicted performance scores align with the actual values. An R² score close to 1 indicates a strong predictive model, while a score near 0 suggests the model is not capturing meaningful patterns in the data. Participants should aim to maximize their R² score by refining feature selection, leveraging all available data sources, and experimenting with different machine learning techniques.


## Submission File
For each id in the test set, you must predict a probability for the performance_score variable. The file should contain a header and have the following format:

```
id,performance_score
8000,52.88427717
8001,52.88427717
8002,52.88427717
8003,52.88427717
8004,52.88427717
8005,52.88427717
```