Leveraging Machine Learning for Online Job Scam Detection

Abstract

The rapid expansion of online recruitment platforms has significantly improved employment accessibility, but it has also led to a substantial increase in fraudulent job advertisements. These deceptive postings often exploit job seekers by collecting sensitive personal information, demanding fraudulent payments, or promoting non-existent employment opportunities. Consequently, the development of intelligent systems capable of automatically distinguishing legitimate job postings from fraudulent ones has become increasingly important. This research presents a machine learning-based framework for online job scam detection using three supervised learning algorithms: Decision Tree, Random Forest, and Extreme Gradient Boosting (XGBoost). The proposed methodology involves comprehensive data preprocessing, including missing value handling, categorical feature encoding, feature selection, and dataset normalization to enhance model performance. The processed data are then used to train and evaluate the selected classification models. Experimental analysis compares the models using performance metrics such as accuracy, precision, recall, F1-score, and confusion matrix. Among the evaluated approaches, the ensemble-based models, particularly XGBoost and Random Forest, demonstrate superior classification capability by effectively identifying fraudulent job postings while minimizing false positives and false negatives. The proposed system offers a reliable and scalable solution that can assist recruitment platforms, organizations, and job seekers in detecting deceptive employment advertisements before they cause financial or personal harm. This work highlights the effectiveness of machine learning techniques in strengthening cybersecurity within online recruitment ecosystems and promoting safer digital hiring practices.