Skip to content

Latest commit

 

History

History
38 lines (22 loc) · 1.54 KB

README.md

File metadata and controls

38 lines (22 loc) · 1.54 KB

Fake-Job-Post-Detection-Using-ML-Approach

A machine learning project to detect fake job postings using Logistic Regression, Random Forest, and XGBoost. Focused on improving recruitment safety by optimizing model accuracy and reducing time complexity. This project aims to identify fake job postings using machine learning techniques. With the rise in online job scams, it's crucial to develop tools that help users differentiate between genuine and fraudulent job offers.

This Flask-based web application allows users to input job details and predicts whether the job post is real or fake using trained machine learning models.

🚀 Features

  • Detects fake job postings using Logistic Regression, Random Forest, and XGBoost.
  • User-friendly web interface built with HTML and CSS.
  • Flask backend for model integration and request handling.
  • Minimal, clean layout with prediction results.

🛠️ Technologies Used

  • Python
  • Flask
  • HTML / CSS
  • scikit-learn, pandas, numpy

🧠 How It Works

  1. Dataset is preprocessed and vectorized using NLP techniques.
  2. Machine learning models are trained (Logistic Regression, Random Forest, XGBoost).
  3. The trained model is integrated into a Flask app.
  4. Users submit job description via web UI → backend predicts whether the job is real or fake.

📽️ Demo Video

Watch how the project works (installation and execution video):

👉 Click here to watch the project demo