Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{204285,
        author = {KODIBOINA NAVYASRI DURGA and Mr. S. LAKSHMANA RAO},
        title = {Smart Hire+: An Intelligent Resume Screening and Candidate Ranking Framework Using Natural Language Processing and Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {1891-1904},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204285},
        abstract = {The increasing volume of job applications received through online recruitment platforms has made manual resume screening a challenging and time-consuming task for organizations. Traditional recruitment approaches often rely on manual evaluation or keyword-based filtering techniques, which may lead to inconsistent candidate assessment and inefficient hiring decisions. To address these challenges, this paper presents SmartHire+, an intelligent resume screening and candidate ranking framework that integrates Natural Language Processing (NLP), Machine Learning (ML), and Learning-to-Rank techniques to automate candidate evaluation and recruitment decision support. The proposed framework extracts and processes information from candidate resumes and job descriptions using text extraction, Optical Character Recognition (OCR), and text preprocessing techniques. Multiple similarity analysis methods, including Term Frequency–Inverse Document Frequency (TF-IDF), Bag-of-Words (BoW), Word2Vec, and Sentence-BERT (SBERT), are employed to measure the relevance between candidate profiles and job requirements. In addition, feature engineering techniques such as skill matching, domain matching, and keyword overlap analysis are incorporated to enhance candidate assessment. Several machine learning algorithms, including Logistic Regression, Random Forest, XGBoost, and Gradient Boosting, are utilized for candidate classification, while a LambdaMART-based Learning-to-Rank model is implemented to prioritize applicants according to their suitability for specific job roles. Experimental results demonstrate the effectiveness of the proposed framework in intelligent recruitment applications. Among the evaluated classification models, Random Forest and Gradient Boosting achieved the highest accuracy of 75.50%. Furthermore, the ranking framework achieved an average Normalized Discounted Cumulative Gain (NDCG) score of 0.9895, indicating excellent candidate prioritization performance. The system also incorporates a skill gap analysis module that identifies missing competencies and generates career and course recommendations to support professional development. A 
Flask-based web application was developed to provide recruiters with an interactive platform for real-time resume analysis and candidate evaluation. The obtained results demonstrate that SmartHire+ effectively improves recruitment efficiency, candidate selection accuracy, and data-driven hiring decision-making.},
        keywords = {Resume Screening, Candidate Ranking, Natural Language Processing, Machine Learning, Learning-to-Rank, LambdaMART, Word2Vec, Sentence-BERT, Skill Gap Analysis, Recruitment Automation.},
        month = {June},
        }