FAKE JOB PREDICTION USING MACHINE LEARNING ALGORITHMS

Abstract

With the proliferation of online job portals and digital recruitment platforms, job seekers are increasingly vulnerable to fake job postings designed to deceive, defraud, or harvest personal data. Manual identification of such fraudulent listings is time-consuming, inconsistent, and often ineffective at scale. This research proposes a machine learning-based approach to automatically predict and detect fake job postings using real-world data. The study utilizes a publicly available dataset containing labeled job listings and implements various classification algorithms including Logistic Regression, Random Forest, Support Vector Machine (SVM), Naïve Bayes, and XGBoost. Comprehensive preprocessing techniques, including natural language processing and feature engineering, are applied to enhance model performance. The models are evaluated using metrics such as accuracy, precision, recall, F1-score, and ROC-AUC. Among the tested algorithms, Random Forest and XGBoost exhibited superior performance with accuracy exceeding 95%. The results demonstrate that machine learning can be effectively leveraged to safeguard users against fraudulent job postings, ensuring a safer digital jobhunting experience. This study lays the groundwork for integrating real-time fraud detection systems within job portals and recruiting platforms