https://github.com/shubhamdeepkeshav/fraud-detection-project

Welcome to the Fraud Detection Project! This repository uses machine learning 🧠 to detect fraudulent transactions 💳. It includes data preprocessing 🛠️, model training 📚, evaluation 📊, and visualization 📈. Explore, experiment, and contribute 🤝 to improve fraud detection accuracy. Check the README for setup and usage instructions.
https://github.com/shubhamdeepkeshav/fraud-detection-project

accuracy datascience frauddectection jupyter-notebook mechinelearning modeltraining python vizualisation

Last synced: 3 months ago
JSON representation

Welcome to the Fraud Detection Project! This repository uses machine learning 🧠 to detect fraudulent transactions 💳. It includes data preprocessing 🛠️, model training 📚, evaluation 📊, and visualization 📈. Explore, experiment, and contribute 🤝 to improve fraud detection accuracy. Check the README for setup and usage instructions.

• Host: GitHub
• URL: https://github.com/shubhamdeepkeshav/fraud-detection-project
• Owner: shubhamdeepkeshav
• Created: 2024-07-15T15:20:35.000Z (10 months ago)
• Default Branch: main
• Last Pushed: 2024-07-15T15:33:25.000Z (10 months ago)
• Last Synced: 2025-01-10T08:58:32.427Z (4 months ago)
• Topics: accuracy, datascience, frauddectection, jupyter-notebook, mechinelearning, modeltraining, python, vizualisation
• Language: Jupyter Notebook
• Homepage:
• Size: 244 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Fraud Detection Project 🕵️

This project focuses on using machine learning algorithms to detect fraud in financial transactions.

# Overview  📋

 The repository contains code for training and evaluating different models to detect fraudulent activities in transaction data. It aims to provide accurate fraud detection capabilities using supervised learning techniques.

# Features 🛠️

    •	Data Preprocessing🛠️: Cleaning, transforming, and preparing the dataset for analysis.

    

    •	Model Training📚: Training classifiers including Random Forest, Decision Tree, Logistic Regression, and K-Nearest Neighbors.

    

    •	Model Evaluation📊: Assessing model performance using accuracy score, ROC curve, Precision-Recall curve, and confusion matrix.

    

    •	Visualization 📊: Visualizing model comparisons, feature importance, and evaluation metrics using matplotlib and seaborn.

    

    •	Deployment🚀: Options for deploying trained models in production environments for real-time fraud detection.

# Files 📁

    •	fraud_detection.ipynb: Jupyter Notebook with code for data preprocessing, model training, evaluation, and visualization.

    

    •	data.csv: Sample dataset used for training and testing.

    

    •	README.md: This file providing an overview of the project.

# Results 📈

    

    •	RandomForest 🌲: Accuracy - 98%

    

    •	DecisionTree 🌳: Accuracy - 97%

    

    •	Logistic Regression 📈: Accuracy - 98%

    

    •	KNN 📏: Accuracy - 98%

   ![Screenshot 2024-07-13 143847](https://github.com/user-attachments/assets/e6ad65a8-53f7-4df8-b934-866f51a40367)

      

# Additional Notes 📝

    

    •	The dataset used in this project contains simulated transaction data.

    

    •	The models are trained and evaluated on a balanced dataset with synthetic fraud cases.