Skip to content

Latest commit

 

History

History

FraudDetection

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
data
data
 
 
model
model
 
 
notebook
notebook
 
 
templates
templates
 
 
.DS_Store
.DS_Store
 
 
README.md
README.md
 
 
app.py
app.py
 
 
requirements.txt
requirements.txt
 
 

README.md

Credit Card Fraud Detection

This project implements a machine learning model to detect fraudulent credit card transactions using anomaly detection techniques like Isolation Forest. The goal is to accurately identify suspicious behavior in an imbalanced dataset.

Dataset

  • Name: Credit Card Fraud Detection
  • Source: Kaggle
  • Size: 150 MB (compressed as data/data.zip)
  • Features:
    • Numerical features (V1 to V28) from PCA transformation
    • Amount – transaction amount
    • Class – target variable (0: Normal, 1: Fraud)

Model Overview

  • Technique: Unsupervised Learning / Anomaly Detection
  • Algorithm: IsolationForest (from sklearn.ensemble)
  • Imbalance Handling: Model trained on full data but flagged only rare anomalies

How to Run

  1. Clone the repository
git clone https://github.com/yourusername/PythonProject.git
cd PythonProject/FraudDetectionApp
  1. **Install dependencies
pip install -r requirements.txt
  1. **Extract dataset
unzip data/data.zip -d data/
  1. **Run the Flask app
python app.py
  1. **Visit your browser

Go to http://127.0.0.1:5000