https://github.com/vishnu-vamshii/fraud-detection-using-machine-learning

Developed a machine learning pipeline to detect fraudulent credit card transactions, handling imbalanced data with SMOTE and scaling. Trained models like Logistic Regression and Random Forest. Conducted EDA to identify fraud patterns.
https://github.com/vishnu-vamshii/fraud-detection-using-machine-learning

pandas python scikit-learn tensorflow

Last synced: about 2 months ago
JSON representation

Developed a machine learning pipeline to detect fraudulent credit card transactions, handling imbalanced data with SMOTE and scaling. Trained models like Logistic Regression and Random Forest. Conducted EDA to identify fraud patterns.

• Host: GitHub
• URL: https://github.com/vishnu-vamshii/fraud-detection-using-machine-learning
• Owner: vishnu-vamshii
• Created: 2024-11-22T07:32:25.000Z (about 2 months ago)
• Default Branch: main
• Last Pushed: 2024-11-22T07:52:06.000Z (about 2 months ago)
• Last Synced: 2024-11-22T08:28:19.085Z (about 2 months ago)
• Topics: pandas, python, scikit-learn, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 0 Bytes
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Credit Card Fraud Detection Using Machine Learning

## 📌 Overview

This project focuses on detecting fraudulent credit card transactions using machine learning techniques. The goal is to build a predictive model that can identify fraudulent transactions with high accuracy, ensuring minimal false positives and negatives.

---

## 💡 Key Features

- **Exploratory Data Analysis (EDA):** Understand trends, correlations, and distributions in the dataset.

- **Data Preprocessing:** Handle class imbalance using techniques like SMOTE, and scale features for optimal performance.

- **Machine Learning Models:** Implement various algorithms including Logistic Regression, Random Forest, and Gradient Boosting.

- **Evaluation Metrics:** Use precision, recall and F1-score to assess model performance.

- **Visualizations:** Include interactive visualizations for model insights and fraud patterns.

---

## 📂 Dataset

The dataset used for this project is the [Kaggle Credit Card Fraud Detection Dataset](https://www.kaggle.com/datasets/mlg-ulb/creditcardfraud). It contains:

- **284,807 transactions** over two days.

- **31 features** including time, amount, and anonymized PCA components.

- An extremely imbalanced target variable where only 0.172% of transactions are fraudulent.

---

## 🛠️ Tech Stack

- **Programming Languages:** Python

- **Libraries:** Pandas, NumPy, Scikit-learn, Matplotlib, Seaborn

- **Machine Learning Techniques:** Logistic Regression, Random Forest, Gradient Boosting

- **Data Balancing:** SMOTE (Synthetic Minority Oversampling Technique)