Lending Club Case Study
- We will try to find out the applicants who are likely to default i.e. not pay the loan.
- this analysis is being done for a company which is the largest online loan marketplace. We will try to minimize the credit loss to this company.
- What is the business probem that your project is trying to solve? - whether to sanction the loan to the applicant or not.
- we have got a loans dataset which has multiple column, we will be focusing on these columns - loan_amt, term, int_rate, grade, emp_title, loan_status, annual_income
- Most of the data is of loan_status Fully paid, there are around 5000 rows with charged off loan status
- most loan amount is in the range of 5000 to 150000
- if the loan duration i.e. is more than 40 months, then the applicant is likely to 'default' or be in 'current' loan status
- if the annual income is less than 60000, then the applicant is highly likely to default
- if the interest rate is above 12, then applicant may 'default' or be in 'current' loan status
- Python 3.7
- Pandas
- Numpy
- matplotlib
- seaborn
Created by [@Viveksingh1313] - feel free to contact me!