Fraud Detection in Online Food Delivery (Fastmeal Case Study)

This repository contains a machine learning project on fraud detection using synthetic transaction data.
It explores supervised and unsupervised approaches to detect fraudulent transactions for a food delivery platform (Fastmeal by Tradeet).

---

Project Overview

Fraud is a critical challenge in online transactions. In this project, fraud detection scenarios was simulated using synthetic data generated with Gretel.ai.

The focus is on comparing:

• Anomaly detection models (Isolation Forest)
• Supervised classifiers (Logistic Regression, Random Forest, XGBoost, Decision Tree)

Their effectiveness was evaluated under high class imbalance (fraud cases are rare).

---

📂 Repository Structure

• data/ → Synthetic dataset(s) and data notes
• notebook/ → Jupyter notebook for exploration, modeling, and evaluation
• reports/ → Figures, plots, and final report write-up

---

⚙️ Setup & Installation

Clone the repo:

git clone https://github.com/Simi-Solola/fraud-detection-fastmeal.git
cd fraud-detection-fastmeal