As a part of a Consumer Lending Finance Company, which specialises in lending various types of loans, we need to identify the patterns which indicates if a loan is likely to Default. When the company receives a loan application, it has to make a decision for loan approval based on applicant's profile. This decisioning is associated with 2 kinds of risks;
a. If the applicant is likely to pay the loan, not approving such loan will result in loss for the company; b. If the applicant is likely to default the loan, approving such loan application will also result in loss.
The data given below contains the information about past loan applicants and whether they ‘defaulted’ or not. We need to perform EDA to understand how consumer attributes and loan attributes infulence the decisioning. In other words, the company wants to understand the driving factors (or driver variables) behind loan default, i.e. the variables which are strong indicators of default. The company can utilise this knowledge for its portfolio and risk assessment.
Driving Factors for loan getting default:
-
Higher Loan Amount (> $30000)
-
Higher interest rate (> 20%)
-
Loan Purpose ( Small Business, Renewable Energy, Education)
-
Higher Revolve Utilization rate (> 75%)
-
Bad Loan Grades (F, G)
-
Lower Annual Income (< $20000)
-
Higher Debt To Income ratio (20% - 25%)
- pandas
- numpy
- matplotlib
- seaborn
- datetime
Pratik Patil
Manish Kumar