Ajay Kumar Garg Engineering College India.
International Journal of Science and Research Archive, 2026, 19(02), 110-119
Article DOI: 10.30574/ijsra.2026.19.2.0995
Received on 18 March 2026; revised on 02 May 2026; accepted on 04 May 2026
Manual resume screening is a difficult, time-consuming, and biased task in today’s recruitment environment due to the tremendous volume of job applications. Modern one-click job portals and remote work trends have accelerated the growth of digital applications, which has greatly exceeded human resource processing skills. Conventional Applicant Tracking Sys-tems (ATS) rely on strict, keyword-based screening algorithms that often reject highly competent applicants because of missing exact-match buzzwords, synonymous terminology, or formatting quirks. This seriously harms the talent acquisition pipeline by giving candidates an opaque ”black-box” experience and producing a high percentage of false negatives for employers.
This study presents a novel, highly scalable Dual-Benefit Framework that parses extremely unstructured resume pa-pers using sophisticated Natural Language Processing (NLP) and Ensemble Machine Learning (ML) approaches, turning unstructured material into organised, useful intelligence. The platform serves as an educational partner for job seekers, offering quick feedback, an overall resume compatibility score, and a thorough, data-driven skill-gap analysis that is directly connected to online learning materials. The system provides recruiters with a centralised dashboard that displays automatic candidate-to-job matching scores based on an optimised Random Forest classification engine, Cosine Similarity, Jaccard Similarity, and Term Frequency-Inverse Document Frequency (TF-IDF) vectorisation. We also investigate methods to prevent adversarial resume manipulation (keyword stuffing), stringent data privacy procedures, and mathematical enforcement of algorithmic fair-ness.This framework reduces recruitment timelines by over 98%, minimises unconscious demographic bias at the point of ingestion, and promotes an equitable, transparent hiring ecosystem for both employers and applicants by actively addressing the Sustainable Development Goals (SDGs) of the United Nations, specifically SDG 4, SDG 8, and SDG 10.
Natural Language Processing (NLP); Machine Learning; Applicant Tracking System (ATS); Skill Gap Analysis; TF-IDF; Named Entity Recognition (NER); Bias Mitigation; Explainable AI (XAI); Random Forest; Adversarial Robustness.
Preview Article PDF
Kavya Mittal, Manthan Awasthi, Kartiekey Bharadwaj, Kartik Gupta and Sheradha Jauhari. A dual-benefit framework for AI-powered resume analysis and job matching: Integrating NLP, machine learning, and skill-gap analytics. International Journal of Science and Research Archive, 2026, 19(02), 110-119. Article DOI: https://doi.org/10.30574/ijsra.2026.19.2.0995.






