BNPL (Buy Now, Pay Later) is a financial service that allows customers to purchase products immediately and pay for them over time through installments.
This project analyzes a simulated BNPL lending dataset to understand customer borrowing behavior, credit risk, and profitability patterns using Power BI.
The dashboard helps answer key business questions such as:
- Which merchant categories generate the most BNPL transactions?
- Which BNPL providers issue the highest loan amounts?
- How does customer credit score influence borrowing behavior?
- Which customer segments are more likely to default?
The goal is to demonstrate how data analytics can support risk management and lending decisions in fintech companies.
| Power BI | DAX | Data Modeling |
|---|
The dataset contains simulated BNPL transaction records including the following fields:
| Column | Description |
|---|---|
| customer_id | Unique identifier for each customer |
| transaction_id | Unique identifier for each transaction |
| principal_ngn | Loan amount issued (in Nigerian Naira) |
| credit_score | Customer credit score |
| merchant_category | Merchant industry category |
| provider | BNPL service provider |
| num_installments | Number of installments chosen |
| default_90d | Whether the loan defaulted within 90 days |
| calculated_interest | Interest earned from the loan |
The following image shows the Power BI dashboard analyzing BNPL lending performance, customer credit risk, and profitability insights.
The dashboard tracks several important lending metrics:
- Total Customers – Number of unique customers using BNPL
- Total Transactions – Total number of loan transactions
- Total Loan Amount – Total value of loans issued
- Total Interest Earned – Revenue generated from loans
- Average Credit Score – Overall customer credit quality
- Default Rate – Percentage of loans defaulting within 90 days
Shows which merchant industries receive the highest BNPL loan amounts.
Compares lending activity between different BNPL providers.
Analyzes customer repayment preferences based on installment selection.
Scatter plot showing the relationship between customer creditworthiness and borrowing behavior.
Customers are segmented into High Risk, Medium Risk, and Low Risk groups based on credit score to identify default patterns.
Credit Risk Segment =
SWITCH(
TRUE(),
bnpl_full_sample[credit_score] < 550, "High Risk",
bnpl_full_sample[credit_score] < 650, "Medium Risk",
"Low Risk"
)
Default Rate =
AVERAGE(bnpl_full_sample[default_90d])
Where:
- TRUE / 1 → Default
- FALSE / 0 → No Default
- Certain merchant categories generate higher BNPL loan volumes.
- Customers with higher credit scores tend to take larger loans.
- Installment choices influence borrowing patterns and repayment behavior.
- High-risk customers show a higher probability of default, highlighting potential risk areas for lenders.
The objective of this project is to demonstrate how data visualization and analytics can help fintech companies monitor lending performance, manage credit risk, and improve profitability.
This project highlights skills in:
- Business Intelligence
- Data Visualization
- Risk Analysis
- Financial Data Analytics
- Data Storytelling