This project explores the key factors influencing credit card eligibility, leveraging a comprehensive dataset of demographic, financial, and personal attributes. The analysis uncovers patterns and relationships that may impact credit card approval decisions, providing insights that financial institutions could use to refine eligibility criteria.
This analysis identifies trends and correlations in credit card approvals, focusing on factors such as housing, income, employment stability, and digital accessibility.
- Trend Identification: Discover key approval trends based on income, housing, and employment duration.
- Correlation Analysis: Examine relationships between approval likelihood and attributes like housing type, occupation, and communication tools.
- Actionable Insights: Provide recommendations to improve credit card eligibility assessments.
The Credit Card Eligibility Dataset from Kaggle includes:
- Demographics: Age, gender, family size.
- Financial Data: Income, account duration, employment years, income type.
- Housing Info: Car and property ownership, housing type.
- Communication Tools: Phone, work phone, and email access.
- Outcome: Whether an individual was approved or denied.
- Employment Stability: Long-term employment does not strongly correlate with approval; short-duration occupations like "IT Staff" also saw approvals.
- Housing Status: Most approvals went to homeowners, but a significant number of applicants living with parents were also approved, indicating flexibility in financial criteria.
- Income & Housing Type: Homeowners generally have higher incomes, with the majority earning between $100,000–$300,000.
- Digital Accessibility: Access to communication tools (phone, email) was not a decisive factor for approval.
- Occupation & Approval: Approval was granted across various occupations, including those with below-average employment duration, challenging the link between job stability and creditworthiness.
- Income & Homeownership: High income correlates with homeownership, but it does not guarantee credit approval.
- Communication Tools: Applicants with no or minimal access to communication tools had similar approval rates, suggesting these factors may be less relevant.
- Sentiment Analysis: Assess customer feedback to understand applicant satisfaction with credit services.
- Enhanced Feature Engineering: Explore debt-to-income ratios or credit obligations for a more detailed creditworthiness assessment.
This repository contains:
- Data Exploration Notebooks: SQL and Excel-based analysis scripts.
- Visualizations: Data visualizations detailing insights into credit approval factors.
- Findings Summary: Key insights on how factors like employment and housing influence credit card eligibility.