Lending Club Case Study

Table of Contents

• General Info
• Contents
• Technologies Used
• Conclusions
• Acknowledgements

General Information

• This repository contains the code and documentation for a data analysis focused on the Lending Club Case Study.

• Problem Statement: Consumer finance company specialises in lending various types of loans to urban customers.When the company receives a loan application, the company has to make a decision for loan approval based on the applicant’s profile. The company aims to reduce credit loss by identifying risky loan applicants. Specifically, they want to understand the driving factors or variables that strongly indicate loan default. The customers labeled as 'charged-off' are considered defaulters.

• Dataset used: loan.csv

Contents

• Notebook: EPGPML58_SachinMahale.ipynb
• Documentation: Learning_Club_Case_Study.pdf

Conclusions

Based on the analysis, following recommendations aim to enhance risk management to reduce default rates:

• Loans with a term of 60 months exhibit a higher default rate.
• Grades G and F display higher default rates compared to others.
• Within G3 and F5 subcategories, default rates are notably high.
• Loans for small_business and renewable_energy categories pose higher risks of default rate.
• States such as NE, NV are identified as having higher default rates.
• Higher Debt to Income Ratio (DTI) depicts an increased likelihood of charged off loans.
• Loans for small_business and renewable_energy categories pose higher risks of default rate.
• Higher loan amounts,interest rates,funded amounts correspond to an increased likelihood of loans being charged off.

Technologies Used

• Seaborn version: 0.12.2
• Matplotlib version: 3.7.0
• Python version: 3.10.9

Contact

Created by [@sachinmahale] - feel free to contact me!