### Metric

The evaluation metric for this competition is the Mean Column ROC AUC. This means we treat each loan as its own binary classification problem, and calculate the area under curve (AUC) of the receiver operating curve (ROC). It allows us to measure a balance of the false positive and true positive rate. It is elaborated on [here](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_auc_score.html).

The equivalent [sklearn command](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_auc_score.html) used by the Kaggle grader would be: 
```
sklearn.metrics.roc_auc_score(y_ground_truth, y_predicted_probability)
```

Submission Format
For every row of data in LOANS_TEST.csv, submission files should contain 2 columns:

```id```: contains integers equal to the id's in the LOANS_TEST.csv file
```loan_status```: contains an integer (0 or 1), with 0 representing that the loan is Fully Paid, and 1 representing that the loan is Charged Off. 

The file should contain a header and have the following format:

```
id,loan_status
200000,0.17
200001,0.20
...
242479,0.67
```