This dataset is provided by one of the banks. Some of the variables are encoded due to confidentiality issues. That's why they are presented in conventional units. It doesen't affect the learning process at all, so feel free to participate.

Variables are presented in categorical and numerical forms.

To make it easier to code, there are they, divided into these 2 categories:
`term`, `sum`, `payment`, `residence_since`, `age`, `credits`, `dependents` are numerical variables.

`status`, `credit_report`, `reason`, `savings`, `employment`, `marital_status`, `guarantees`, `estate`, `other_credits`, `accommodation`, `qualification`, `phone` and `immigrant` are categorical.

`id` is the identification number of an example, `bancruptcy` is the target variable in the train set.

Variables description is presented in the datasets variables description.

The game is on!