The evaluation metric for this competition is
[RMSE (Root Mean Squared Error)](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.auc.html)
. The RMSE, commonly used in regression models, gives an idea of the prediction error in the same units as the target, in our case length of stay in days. It's the root square of Mean Squared Error, which is another popular measure of error.
Overall, RMSE is a measure of accuracy, to compare forecasting errors of different models for a particular dataset and not between datasets, as it is scale-dependent.<\p>
Submission Format
For every patient in the test dataset
, submission files should contain two columns: icustayid (this defines the individual prediction, and it's extracted from the test dataset) and LOS (float positive number, length of stay in days).
The file should contain a header and have the following format:
icustay_id,LOS
1346,2.3
You can check the sample submission file mimic_kaggle_los_sample_submission.csv.