A python program to study the risk behaviour of the loan application for the provide loan data set.
- A python program to study the risk behaviour of the loan application for the provide loan data set.
- The application of EDA is to understand how consumer attributes and loan attributes influence the tendency of default.
- If the loan applicant is not likely to repay the loan, i.e. he/she is likely to default, then approving the loan may lead to a financial loss for the company.
- We have been provided with the Private Data of Lending Club. The complete loan data for all loans issued through the time period 2007 to 2011.
-
Approximately 14% of loans in the provided dataset are defaulted.
-
Maximum number of loan disbursed is from 5000 to 10000. Maximum number of loan disbursed in the year 2011 alone which is more than 50%.
-
Predominantly, most of the loan applicant either have mortgage something or living in a rented place, and the same category reflects for the defaulters, combining both of them are 93% of default case.
-
Giving loan for debt consolidation purpose is a riskier business, more than half of them (out of total default case) can default.
-
10+ years employees contribute for loan defaulting upto 30%, i.e., one third of total default cases.
-
Avoid giving loan to the applicant who has even one public derogatory record.
-
When dept payment to income ratio is higher than 15, they are likely to default.
-
Other than very income group, annual income does not affect the loan defaulting.
-
Grade employee (E, F & G) have given the most profits to the lending company with high interest rate suitably with 15-22% rate.
-
States WY has the highest average(median) loan amount that was charged off. This state must be looked into by the LC for further investigation.
- Jupyter Notebook - version 6.4.5
- VS Code - version 1.65.0
- Python - version 3.9.7
- Pandas - version 1.3.4
- Numpy - version 1.20.3
- Matplotlib - version 3.4.3
- Seaborn - version 0.11.2
- Plotly - version 4.14.3
- This project was the case study from the Upgrad. We are thankful to the Upgrad & IIIT, Bangalore for providing the necessary knowledge & support.
- Other references is taken form the various internet source.
Created by [@vijaypss] - feel free to contact me!