Credit Card Approval Prediction

Overview of the Project

This project is to help Providence Bank** to minimize two basic risks inherent in its credit card business:

Opportunity loss resulting from the denial of “Good” credit card applicants.

Financial loss resulting from approving non-credit worthy applicants.

To help the bank address the above, a Machine Learning model will be developed to process credit card applications.

It is very important to manage credit risk and handle challenges efficiently for credit decision as it can have adverse effects on credit management.

** Fictitious name used

Topic Selection Criteria

The current global economy is relatively precarious – in the last year $24 trillion has been added to the global debt – a total record high of $281 trillion and debt-GDP ratio of over 355% (source Reuters London).

Financial institutions will be looking for ways to minimize the risks associated with the many sectors they are involved in.

The credit card charge-off rates have increased to 3.76% compared to 0.93% for other consumer credit products (source Federal Reserve reports).

Credit cards being one of the major income segments for banks, new models that help these institutions mitigate the risks involved in extending credit to their clients will be very sought after.