InJobs - Interconnected Network Job Search

The demand for part-time employment among stu- dents has increased significantly due to rising educational costs and the need for financial independence. However, existing job platforms are not designed to meet student-specific requirements such as flexibility, entry-level accessibility, and security from fraudulent job postings. This paper presents InJobs, an AI- driven web platform that integrates job recommendation, fraud detection, and skill development into a unified system. The platform utilizes BERT-based semantic matching for accurate job recommendations and a Random Forest classifier for fraud detection. Additionally, a learning and certification module is incorporated to bridge the gap between skill acquisition and employment. Experimental evaluation demonstrates improved recommendation relevance, high fraud detection accuracy, and efficient system performance. The proposed system aims to provide a secure, intelligent, and student-focused employment ecosystem.