ONLINE RECRUITMENT FRAUD(ORF) DETECTION USING DEEP LEARNING APPROACHES

Abstract

Online recruitment has become a widely adopted process for connecting employers and job seekers through digital platforms. However, the increasing reliance on online recruitment systems has also led to a rise in Online Recruitment Fraud (ORF), where fraudulent job advertisements, fake recruiters, and deceptive employment offers are used to exploit job applicants. Such fraudulent activities can result in financial losses, identity theft, and reduced trust in online recruitment platforms. Traditional fraud detection methods often struggle to identify sophisticated and evolving recruitment scams due to the large volume of online job postings and the diversity of fraudulent techniques. This paper presents an Online Recruitment Fraud Detection framework using deep learning approaches. The proposed system analyzes job advertisements, recruiter information, company details, and textual content using Natural Language Processing and deep learning models to identify fraudulent recruitment activities. Advanced neural network architectures automatically learn complex patterns and semantic relationships within recruitment data, enabling accurate classification of legitimate and fraudulent job postings. Experimental analysis demonstrates that the proposed deep learning framework achieves high detection accuracy, reduces false alarm rates, and enhances the security of online recruitment platforms. The developed system provides an intelligent and scalable solution for protecting job seekers and maintaining the integrity of digital recruitment ecosystems.