A ROBUST HYBRID MACHINE LEARNING PIPELINE FOR IDENTIFYING JOB SCAMS ONLINE

With the rapid expansion of online recruitment platforms, fake job advertisements have emerged as a serious concern, often resulting in identity theft, financial fraud, and the manipulation of innocent job seekers.To combat this growing challenge,we present a hybrid machine learning based solution designed to detect and classify fraudulent job postings with high precision. The system is versatile, accepting job-related inputs in multiple forms such as text, website links, and images, making it suitable for real world deployment across various job platforms.After extraction,the collected information is organized into CSV datasets and analyzed using multiple classification models,including Naive Bayes, Random Forest, Support Vector Machine (SVM), and XGBoost. By combining the predictive capabilities of these algorithms, the model achieves robust and reliable identification of authentic versus scam job listings.Ultimately, this approach strengthens online hiring security and assists job seekers in identifying legitimate opportunities with greater trust and confidence.