Submissions are evaluated on [accuracy score](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.accuracy_score.html) between the predicted label and the true target.

You should also write a description and make your notebook public after the submission deadline so we can understand your approach and check whether it complies with the rules (to check them out, use the link above). [Here](https://www.kaggle.com/discussions/product-feedback/373153), you can find a description about creating a write-up attached to your best submission, which will be visible after the competition ends.

## Submission File
For each prediction_id in the test set, you must predict whether two content samples come from the same author. 1 corresponds to samples from the same author and 0 otherwise. The file should contain a header and have the following format:

    prediction_id,label
    0,0
    1,1
    2,1
    3,0
    etc.