The rapid growth of online recruitment platforms has led to an increase in fake job postings, posing serious risks to job seekers and undermining trust in digital employment ecosystems. This paper proposes a machine learning-based system for detecting fraudulent job advertisements by analyzing textual and structural features of job postings. A comprehensive dataset was preprocessed and featureengineered to capture suspicious patterns such as keyword frequency, email domain type, and salary disclosure. Multiple classification algorithms, including Support Vector Machine (SVM), Decision Tree, Naïve Bayes, K-Nearest Neighbors (K-NN), and Random Forest, were trained and evaluated. Among them, Random Forest achieved the highest performance with an accuracy of 96.4%, demonstrating its robustness in handling complex patterns. The study also explored model performance across different training epochs, identifying epoch 20 as the optimal convergence point. The proposed system offers an efficient, scalable, and automated solution for fake job detection, enhancing the safety and integrity of online job markets. A dataset comprising over 17,000 job postings (both real and fake) was used for training and evaluation. Key features such as suspicious keyword count, job description length, email domain type, and salary presence were extracted and analyzed. Five machine learning algorithms— Support Vector Machine (SVM), Decision Tree, Naïve Bayes, K-Nearest Neighbors (K-NN), and Random Forest—were implemented. Among them, the Random Forest algorithm achieved the highest accuracy of 96.4%, with precision of 95.8%, recall of 96.9%, and an F1-score of 96.3%. SVM followed closely with an accuracy of 94.8%, while the lowest was K-NN at 87.6%. Model performance across 30 training epochs was also analyzed, with convergence observed at epoch 20, where the loss minimized to 0.139. These results confirm the effectiveness of the proposed model in accurately detecting fake job postings, offering a scalable and automated solution to enhance the trust and safety of digital hiring platforms.
Goud et al. (Tue,) studied this question.