https://github.com/gui-sitton/bank-loans
In this project I will prepare a report for a bank's loan division. I find out whether a customer's marital status and number of children have an impact on loan default, as well as other factors
https://github.com/gui-sitton/bank-loans
data data-analysis data-analysis-python data-science data-visualization python
Last synced: 12 months ago
JSON representation
In this project I will prepare a report for a bank's loan division. I find out whether a customer's marital status and number of children have an impact on loan default, as well as other factors
- Host: GitHub
- URL: https://github.com/gui-sitton/bank-loans
- Owner: Gui-Sitton
- Created: 2023-06-01T17:42:33.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2023-09-04T13:07:53.000Z (over 2 years ago)
- Last Synced: 2025-01-24T09:12:28.297Z (about 1 year ago)
- Topics: data, data-analysis, data-analysis-python, data-science, data-visualization, python
- Language: Jupyter Notebook
- Homepage:
- Size: 74.2 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Risk of loan default analysis
In this project I will prepare a report for the loan division of a bank. I'm finding out whether a customer's marital status and number of children have an impact on loan default. The bank already has some data on customers' creditworthiness.
I need to create a credit score for a potential customer. A credit score is used to assess a potential borrower's ability to repay their loan.
**Questions Answered in the Project**
1. is there any relationship between having children and paying back a loan on time?
2. Is there any relationship between marital status and paying back a loan on time?
3. Is there a relationship between income level and paying back a loan on time?
4. How do the different purposes of the loan affect the timely payment of the loan?
**Column Description**
* children : the number of children in the family
* days_employed : how long the client has worked
* dob_years : the client's age
* education : the client's level of education
* education_id : customer's education identifier
* family_status : customer's marital status
* family_status_id : customer's marital status identifier
* gender : customer's sex
* income_type : customer's type of income
* debt : if the client has already defaulted on a loan
* total_income : monthly income
* purpose : reason for taking out a loan
**Conclusions**
After analyzing the data, I concluded that:
1. having children does not seem to be a factor that increases the default rate, because even if it has increased by 2% from 0 children to 1, it is little and with 3 children the rate drops, becoming similar to 0 children.
2. It seems that people who have not been married to another person are more likely to default, even if they have a civil partnership.
3. The person's income group doesn't seem to have much influence either, but the richest have the lowest rate, followed by the poorest. This makes the 'middle' groups the most likely to default.
4. The reason for credit is not conclusive, but something personal.
**General conclusion**
Wealthier people who have been through or are in a marriage with no children or more than two tend to pay back their loans more.