A loan is money borrowed to someone (the debtor) with the intent to pay back at an agreed date. Ideally, things should go as planned but when the debtor fails to pay the person they borrowed the loan from (the creditor), the debtor is said to have defaulted on the loan. It is then important for creditors/loan companies to know/predict if a certain debtor will default or not. This is a problem that machine learning solves, this is a classification machine learning problem. As with every machine learning problem, data is the major ingredient in solving it.

The dataset contains information about credit applicants. Banks, globally, use this kind of dataset and type of informative data to create models to help in deciding on who to accept/refuse for a loan. After all the exploratory data analysis, cleansing and dealing with all the anomalies we might (will) find along the way, the patterns of a good/bad applicant will be exposed to be learned by machine learning models. The goal is to train the best machine learning model to maximize the predictive capability of deeply understanding the past customer's profile minimizing the risk of future loan defaults. The metric used for the models' evaluation is the ROC AUC given that we're dealing with a highly unbalanced data.

In the good old days of banking, your chances of getting a loan often depended on how well you knew the bank manager and your reputation as a trustworthy customer. Banks were reluctant to lend to those who posed a credit risk or lacked credit history, and thus being unable to repay loans. Banks, as far as possible, tried to minimise loan defaults and get into an arduous debt recovery process. Since the turn of the century, however, the banking and financial industry has evolved and innovated in ways not seen before. The emergence of fintechs -- especially digital lenders and financing startups -- has made the disbursal of all kinds of loans so easy that you can now obtain a personal or an unsecured loan at the click of a mouse.

One final possibility: regulations dictate that you need to fully describe your model. In that case, it could be useful to have human-readable internals for reference.