Machine Learning Approach in Predicting Fraudulent Job Advertisement

Abstract

As the world population grows, the demand for workers increases, leading to a rise in online job advertisements to connect employers with potential employees on a national scale. However, this shift also brings the risk of falling victim to fraud. Reported commercial crimes in Malaysia saw a 15.3% increase in 2021, with fraud being the highest among them. Several studies have proposed Machine Learning models to classify genuine and fraudulent job advertisements, but the analysis of certain techniques remains limited. The paper aims to develop a predictive model for identifying fraudulent job advertisements using selected features from imbalanced and balanced datasets. The Employment Scam Aegean Dataset was utilized to build Machine Learning classification models using Logistic Regression, Support Vector Machine, Decision Tree, and Naïve Bayes algorithms. These models were combined with different vectorizers like Term Frequency-Inverse Document Frequency, Bag of Words, and Hash. The Decision Tree model with Bag of Words vectorizer on a balanced dataset outperformed other models, achieving an accuracy of 0.705, precision of 0.73, recall of 0.70, F1-score of 0.71, and Area Under Curve score of 0.68. This model shows promise in effectively identifying fraudulent job advertisements, safeguarding job seekers from scams in the online job market.