# Chargeback Risk Analysis

## Objective

Analyze customer transaction behavior to identify high-risk profiles based on chargeback rate and financial impact.

## Context

This project simulates a real-world fraud prevention scenario, focusing on chargeback monitoring, customer risk segmentation and loss analysis.

## Technologies

- SQL

- Python

## Analysis Performed

- Chargeback rate calculation per customer

- Identification of high-risk customer profiles

- Financial loss estimation

- Risk-based segmentation

## Key Insights

- Customers with higher transaction frequency may present higher chargeback exposure

- Chargeback concentration can indicate risky behavior patterns

- Monitoring customer risk helps prioritize preventive actions

## Project Structure

- sql/analysis.sql → main analytical queries

- insights/conclusions.md → business insights and findings

## Next Steps

- Add Python analysis layer

- Create dashboard for chargeback monitoring

- Expand rules for fraud-risk prioritization