AI-Based Job Portal with Intelligent Resume Matching

This research presented an AI-based job portal designed to improve the effectiveness and efficiency of the recruitment process through intelligent resume matching. By integrating Natural Language Processing and Machine Learning tech niques, the proposed system overcomes the limitations of traditional keyword-based job portals and enables semantic understanding of resumes and job descriptions. Experimental evaluation demonstrated that the system significantly enhances matching accuracy, reduces resume screen ing time, and provides reliable candidate ranking based on contextual relevance. The use of TF-IDF and cosine similar ity ensures consistent and scalable performance, making the system suitable for handling large volumes of job applications. Overall, the proposed AI-driven recruitment framework of fers a practical and efficient solution for automated candidate shortlisting and decision support. It has the potential to im prove hiring quality, reduce recruiter workload, and enhance the overall job-matching experience for both employers and job seekers.

[1]   J. Smith et al., “AI in Recruitment Systems,” IEEE Access, 2022. (al, 2022) [2]  A. Kumar, “Resume Matching Using NLP,” IJCSIT, 2021. (A.Kumar, 2021) [3]   M. Brown, “Machine Learning for Hiring Automation,” Springer, 2020. (M.Brown, 2020) [4]   R. Bharathi et al., “Automated Resume Classification System,” IJCA, Vol. 182(43), 2019. (al R. e., 2019) [5]   P. Sharma and A. Gupta, “AI-Powered Applicant Screening Using Ma chine Learning,” IEEE Xplore, 2020. (A.Gupta, 2020) 6] S. Singh et al., “Intelligent Job Recommendation Using NLP,” IRJET, Vol. 8(2), 2021. (al S. e., 2021) [7]   Google AI Research, “Natural Language Understanding in Recruitment,” 2022. (research, 2022) [8]   LinkedIn Engineering Blog, “How AI Improves Job Matching,” 2024. (blog, 2024) [9]     J. Ramos, “Using TF-IDF to Determine Word Relevance in Document Queries,” Proceedings of the First Instructional Conference on Machine Learning, 2003. (J.RAMOS, 2003) [10]  J. Devlin, M. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” Proceedings of NAACL-HLT, pp. 4171–4186, 2019. (J.DEVLIN, 2019)