Submissions are evaluated on a weighted version of the [Pearson correlation coefficient](https://en.wikipedia.org/wiki/Pearson_correlation_coefficient). You can find additional details in [the 'Prediction Details and Evaluation' section of this tutorial notebook](https://www.kaggle.com/cstein06/tutorial-to-the-g-research-crypto-competition).

You must submit to this competition using the provided python time-series API, which ensures that models do not peek forward in time. To use the API, follow this template in Kaggle Notebooks:

```
import gresearch_crypto
env = gresearch_crypto.make_env()   # initialize the environment
iter_test = env.iter_test()    # an iterator which loops over the test set and sample submission
for (test_df, sample_prediction_df) in iter_test:
    sample_prediction_df['Target'] = 0  # make your predictions here
    env.predict(sample_prediction_df)   # register your predictions
```

[A more detailed introduction to the API is available here](https://www.kaggle.com/sohier/detailed-api-introduction).

You will get an error if you submission includes nulls or infinities.