ONLINE RECRUITMENT FRAUD DETECTION USING AI PATTERNS

Abstract

The world population grows and demand for workers increases, leading to a rise in online job advertisements to connect employers with potential employees on a national scale. Machine learning is a powerful tool for finding complex financial security threats that constantly evolve and can be difficult to predict. The findings contribute to a deeper understanding of AI's capabilities and limitations providing insights that can guide the development and deployment of AI driven security systems. The fake jobs is precisely detected and classified from a pool of job posts of both fake and real jobs by using advanced deep learning as well as machine learning classification algorithms. The intervention of AI not only automates a particular task is improves efficiency by many folds. Cybercriminals is targets from globe time. In strategic decision making is important and logical decision model is one of the still unanswered cyber security method. Machine learning algorithms are constantly being improved to identify error data that might indicate a security threats. We used four classes of features: empirical rule set-based features, bag-of-word models, most recent state-of-the-art word embedding and transformer models for various machine learning classifier. The machine learning models were validated by evaluating them on a publicly available job description dataset