Supervised ML Approach to Fake Job Post Detection

The significance of online job platforms has expanded considerably over time. However, along with technological advancements, there has been a rise in fraudulent job postings that aim to exploit job seekers. These fake job listings often mislead users by offering unrealistic opportunities, requesting personal information, or demanding money, which may lead to financial loss and data misuse. Such fraudulent postings pose a serious threat to users by spreading misleading and harmful content. Therefore, there is a strong need for an efficient and reliable detection system. This project addresses the problem of identifying fake job postings by analyzing job- related textual data using machine learning techniques. Various supervised learning algorithms, including Random Forest, Decision Tree, Logistic Regression, and Naive Bayes, along with TF-IDF-based feature extraction, are utilized to classify job postings as real or fake.