Performance of the logistic regression model will be measure by its power to separate good and bad clients - Gini coefficient.

##Submission Format
For every out of sample application ID (SK\_ID\_CURR), submission files should contain two columns: SK\_ID\_CURR and estimated probability of default or its logit transformation (score).

The file should contain a header, be in cvs file with comma as a separator. First column is named SK\_ID\_CURR and the second one SCORE.

```
SK_ID_CURR,SCORE
1111111,0.1
```