Survey on Resume Parsing Models for JOBCONNECT+: Enhancing Recruitment Efficiency using Natural language processing and Machine Learning

• Published in: International Journal of Computational and Experimental Science and Engineering Vol. 10; no. 4
• Main Authors: R. Deepa, V. Jayalakshmi, K. Karpagalakshmi, S. Manikanda Prabhu, P.Thilakavathy
• Format: Journal Article
• Language: English
• Published: 15.12.2024
• ISSN: 2149-9144; 2149-9144
• DOI: 10.22399/ijcesen.660

Due to the rapid rise of digital recruitment platforms, accurate and fast resume processing is needed to speed hiring. JOBCONNECT+-specific resume processing algorithms and recruitment improvements are extensively covered in the investigation.  Better resume parsing technologies may reduce candidate screening time and resources, which this survey may encourage. Despite breakthroughs in Natural language processing and Machine Learning (NLP and ML), present algorithms fail to extract and categorise data from different resume forms, hindering recruiting. The Multi-Label Parser Entity Recognition Model (M-LPERM) employs entity recognition and multi-label classification to increase resume parsing accuracy and flexibility to handle the explosion of candidate data and the complexity of modern resume formats. The adaptable approach satisfies JOBCONNECT+ criteria and handles resume formats with varying language, structure, and content. Automatic candidate shortlisting, skill gap analysis, and customised job suggestions are included in this research. In a complete simulation examination, M-LPERM is compared to existing models for accuracy, processing speed, and resume format adaptability.