Skip to content

The Fake Product Review Detection System is a machine learning-powered web application designed to analyze and detect fake reviews on eCommerce platforms. It helps users identify whether a product has genuine or manipulated reviews by leveraging Natural Language Processing (NLP) and supervised learning models.

Notifications You must be signed in to change notification settings

its-maneeshk/Fake-Product-Detection-System

Repository files navigation

Fraud Filter - Fake Product Detection System

Fake Product Review Detection System πŸ“Œ
The Fake Product Detection System is a machine learning-powered web application that helps users identify whether a product has genuine or manipulated reviews on eCommerce platforms. It leverages Natural Language Processing (NLP) and supervised learning models to analyze reviews and detect fake ones.


🌟 Features

Feature Description
Fake Review Detection Classifies reviews as Fake or Original using a trained ML model.
User-Friendly Interface Simple, intuitive UI built with React & Tailwind CSS.
API Integration Connects to a Flask backend for real-time predictions.
Data Upload Support Allows users to upload CSV datasets for batch analysis.
Visualization & Insights Displays review authenticity percentage with meaningful insights.
Fast & Efficient Processing Uses vectorization techniques for quick text analysis.

πŸ›  Tech Stack

βœ… Frontend: Vite + React + Tailwind CSS
βœ… Backend: Flask (REST API)
βœ… Machine Learning: Scikit-learn (Logistic Regression)
βœ… Model Storage: Joblib for saving/loading .pkl models
βœ… Data Processing: Pandas & NumPy


πŸ“Œ How It Works ?

1️⃣ Train the Machine Learning model using real & fake review datasets.
2️⃣ Save the trained model as fake_review_model.pkl.
3️⃣ Run the Flask backend server to expose a REST API.
4️⃣ Connect the React frontend to interact with the API.
5️⃣ Upload or enter product reviews to get authenticity results.

⚑ This system empowers consumers to make informed purchasing decisions by identifying fraudulent product reviews!


πŸ“‚ Project Directory Structure

FraudFilter - Minor Project/
│── backend/
β”‚   β”œβ”€β”€ .venv/                     # Virtual environment (version = 3.13.2) 
β”‚   β”œβ”€β”€ ml/                        # ML-related scripts and utilities  
β”‚   β”œβ”€β”€ model/                     # Trained ML models  
β”‚   β”œβ”€β”€ scraped_files/             # Stores scraped eCommerce reviews  
β”‚   β”œβ”€β”€ uploads/                   # Stores uploaded files for analysis  
β”‚   β”œβ”€β”€ utils/                     # Helper functions for backend  
β”‚   β”œβ”€β”€ app.py                     # Main Flask API file  
β”‚   β”œβ”€β”€ requirements.txt           # Python dependencies  
│── frontend/
β”‚   β”œβ”€β”€ node_modules/              # Dependencies for frontend  
β”‚   β”œβ”€β”€ public/                    # Public assets like index.html  
β”‚   β”œβ”€β”€ src/                       # React source files  
β”‚   β”‚   β”œβ”€β”€ components/            # Reusable React components  
β”‚   β”‚   β”œβ”€β”€ assets/                # Images, icons, etc.  
β”‚   β”‚   β”œβ”€β”€ utils/                  # Utility functions  
β”‚   β”œβ”€β”€ .env                        # Environment variables  
β”‚   β”œβ”€β”€ .gitignore                  # Git ignore file  
β”‚   β”œβ”€β”€ eslint.config.js            # ESLint configuration  
β”‚   β”œβ”€β”€ index.html                  # Main HTML file  
β”‚   β”œβ”€β”€ package.json                # Frontend dependencies  
β”‚   β”œβ”€β”€ package-lock.json           # Lockfile for package versions  
β”‚   β”œβ”€β”€ postcss.config.js           # PostCSS configuration  
β”‚   β”œβ”€β”€ README.md                   # Project documentation  
β”‚   β”œβ”€β”€ tailwind.config.js          # Tailwind configuration  
β”‚   β”œβ”€β”€ vite.config.js              # Vite configuration  

πŸ“¦ Installation & Setup

πŸ”Ή Prerequisites

Ensure you have the following installed on your system:

  • Python 3.8+
  • Node.js & npm
  • pip (Python package manager)
  • Virtual env (recommanded: use virtual environment if accidently installed requirements globally use "pip uninstall -r requirements.txt -y")

πŸ”Ή Backend Setup (Flask API)

# Navigate to the backend folder
cd backend

# Create a virtual environment (optional but recommended)
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt
#[recommanded: use virtual environment if accidently installed requirements globally use "pip uninstall -r requirements.txt -y]

# Run the Flask server
python app.py

πŸš€ Flask API will start at http://127.0.0.1:5000/

πŸ”Ή Frontend Setup (React + Vite + Tailwind CSS)

# Navigate to the frontend folder
cd frontend

# Install dependencies
npm install

# Start the development server
npm run dev

πŸš€ React app will run at http://localhost:5173/


πŸ“Έ Demo Screenshots

Interface Preview
HOME
WORKING
ABOUT
CONTACTS
BLOGS
FAQ's
MODEL TRY PAGE
USING CSV FILE
USING PRODUCT LINK

πŸ“Œ More detailed UI screenshots can be found in the project_images/ folder.


Disclaimer

This project is developed for educational and research purposes only. We have used publicly available product reviews from Flipkart to analyze and detect fake reviews. No part of this project is intended for commercial use or to infringe on Flipkart’s rights. All trademarks and product information belong to their respective owners. If required, we are willing to remove any data or content upon request.


πŸ”— Contributing

πŸ’‘ Want to contribute? Fork the repo, create a branch, and submit a pull request. I welcome bug fixes, feature improvements, and optimizations.


πŸ“¬ Contact

πŸ’» Developed by Manish Patel

πŸ“§ Email: maneeshkurmii@gmail.com
πŸ”— LinkedIn: itsmaneeshk
πŸ“· Instagram: its_maneeshk_


πŸ† Tech Badges

Python Badge Git Badge Flask Badge React Badge Open Source Badge


πŸ”Ή Follow my work on GitHub & let's build something amazing together! πŸš€

About

The Fake Product Review Detection System is a machine learning-powered web application designed to analyze and detect fake reviews on eCommerce platforms. It helps users identify whether a product has genuine or manipulated reviews by leveraging Natural Language Processing (NLP) and supervised learning models.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •