RECRUITSHIELD: INTELLIGENT DEEP LEARNING MODEL FOR SECURING ONLINE JOB MARKETPLACES

Abstract

The rise of digital recruitment platforms has transformed the hiring process, connecting millions of job seekers with potential employers. However, this digital revolution has also paved the way for recruitment fraud, where malicious actors post fake job listings to extract personal or financial information from unsuspecting applicants. Traditional fraud detection methods relying on rule-based filtering or manual review are insufficient in handling the large volume and sophistication of modern fraudulent activities. This study introduces RecruitShield, an intelligent deep learning-based framework for the detection of online recruitment fraud. The system leverages Natural Language Processing (NLP) and Deep Neural Networks (DNNs) to analyze job descriptions, employer metadata, and behavioral features to differentiate between legitimate and fraudulent postings. Experimental results demonstrate that RecruitShield achieves superior accuracy and robustness compared to conventional machine learning approaches. By combining semantic text analysis with deep learning explainability, the proposed model not only enhances detection precision but also promotes trust and transparency in online job marketplaces.