Problem

A consumer finance company specializing in providing loans to urban customers has to decide whether to approve or reject loan applications based on the applicant's profile. The company faces two types of risks: approving a loan for an applicant who is likely to default may lead to financial loss, while rejecting a loan for an applicant who is likely to repay results in a loss of business. The aim is to identify patterns indicating that a person is likely to default, which can be used to deny the loan, reduce the loan amount, lend at a higher interest rate, etc.

The company needs to understand the driving factors behind loan default and identify risky applicants using exploratory data analysis (EDA). This knowledge can be utilized for portfolio and risk assessment, reducing credit loss and cutting down on the amount of financial loss incurred by lending companies.

Learn more about EDA here.

Solution

We conducted exploratory data analysis on past loan applicants' data to identify patterns indicating that a person is likely to default. We analyzed consumer attributes and loan attributes that influence the tendency of defaulting. Using Python programming language, we wrote all our code in one well-commented file and briefly mentioned insights and observations from the analysis.

We presented our overall approach in a presentation that included an explanation of the problem statement and analysis approach. We explained the results of univariate analysis, bivariate analysis, etc., in business terms. We included visualizations and summarized the most important results in the presentation.

Impact

Identified patterns indicating that a person is likely to default, which can be used to deny the loan, reduce the loan amount, lend at a higher interest rate, etc.
Reduced credit loss and cut down on the amount of financial loss incurred by lending companies.

"Quote of how incredible of an impact this had."

Team

Team Member #1 - Data Analyst
- Analyzed consumer attributes and loan attributes that influence the tendency of defaulting using Python programming language.
- Briefly mentioned insights and observations from the analysis in one well-commented file.
- Presented overall approach in a presentation that included an explanation of the problem statement and analysis approach.
- Explained results of univariate analysis, bivariate analysis, etc., in business terms. Included visualizations and summarized the most important results in the presentation.

Reducing Loan Defaults with Exploratory Data Analysis