Job Fraud Detection Application

-> Live: https://job-posting-authenticity-analysis.onrender.com

Overview

This project is a web-based application designed to detect fraudulent job postings. Using machine learning models and a user-friendly interface, the application predicts whether a job posting is legitimate or fraudulent based on the provided job description.

---

Features

• Multi-Model Prediction:
  • Predictions from five machine learning models: Naive Bayes, SVM, Random Forest, XGBoost, and Logistic Regression.
• User-Friendly Interface:
  • A simple, responsive web interface for inputting job descriptions and viewing predictions.
• Real-Time Results:
  • Displays predictions from all models along with a final aggregated result.
• Keyword-Based Fraud Detection:
  • Quick identification of fraudulent postings based on specific keywords.

---

Tech Stack

Front-End

• HTML: Structuring the web page.
• CSS: Styling the interface for a modern, responsive design.

Back-End

• Flask: Web framework for handling requests and rendering templates.
• Python: Logic for integrating machine learning models and processing input.

Machine Learning

• Models used: Naive Bayes, SVM, Random Forest, XGBoost, Logistic Regression.
• Libraries: Scikit-learn, XGBoost, Pandas, NumPy, Pickle.

---