Machine Learning-based Fraud Detection for E-commerce and Banking Transactions

The Fraud Detection project for E-commerce and Banking Transactions aims to significantly improve the identification of fraudulent activities within these sectors. It focuses on developing advanced machine learning models that analyze transaction data, employ sophisticated feature engineering techniques, and implement real-time monitoring systems to achieve high accuracy in fraud detection.

Table of Contents

1. Exploratory Data Analysis (EDA)
2. Model Building and Training
3. Model Explainability Using SHAP
4. Model Deployment and API Development
5. Contributing
6. License

1. Exploratory Data Analysis (EDA)

Univariate Analysis

Bivariate Analysis

Feature Engineering

2. Model Building and Training

After training and testing six models (three for each dataset), we selected the following models:

2.1 Fraud-IP Dataset - XGBoost Model

2.2 Credit Card Dataset - Logistic Regression with StandardScaler

3. Model Explainability Using SHAP

Summary Plot

Force Plot

4. Model Deployment and API Development

Running the Flask App

Testing the API

Building Docker Image

Running Docker Container

Testing the API from Postman

Generated 3 new instances and sent a request to the fraud detection model api.

Contributing

Contributions are welcome! Please fork the repository and submit a pull request.

License

This project is licensed under the MIT License. See the LICENSE file for details.