Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM60707
Volume:
10 |
4 |
April 2026
Pages:
1-3
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer Science and Engineering
Parul University, Gujarat, India
Computer Science and Engineering
Parul University, Gujarat, India
Computer Science and Engineering
Parul University, Gujarat, India
Computer Science and Engineering
Parul University, Gujarat, India
The recruitment process often requires evaluating a large number of resumes, making manual screening inefficient and prone to inconsistencies. Traditional Applicant Tracking Systems (ATS) rely heavily on keyword-based filtering techniques, which frequently fail to capture the contextual meaning of candidate profiles in relation to job requirements. This research proposes an AI-driven resume shortlisting framework that utilizes Natural Language Processing (NLP), semantic similarity analysis, and explainable scoring techniques to automate candidate evaluation. The proposed system extracts structured information from unstructured resume documents and converts both resumes and job descriptions into semantic embeddings. A weighted ranking model evaluates candidates based on skill relevance, professional experience, project similarity, and educational qualifications. To ensure fairness, bias-sensitive attributes are masked during evaluation. Furthermore, an explainable AI component provides interpretable insights into candidate rankings. Experimental evaluation demonstrates that the proposed framework improves matching accuracy and significantly reduces resume screening time compared to conventional keyword-based approaches. The system provides a scalable, transparent, and ethical solution that can be integrated into modern recruitment platforms.
KEYWORDS
This research presented an AI-driven resume shortlisting framework that integrates Natural Language Processing, semantic similarity analysis, explainable scoring mechanisms, and bias-aware evaluation techniques to automate the recruitment screening process. Unlike traditional keyword-based methods, the proposed system captures contextual relationships between resumes and job descriptions, resulting in more accurate candidate ranking. The experimental results demonstrate improvements in shortlisting accuracy, substantial reduction in screening time, and increased transparency through explainable decision outputs. The inclusion of bias-mitigation strategies further ensures that candidate evaluation remains fair and focused on job-relevant qualifications. Overall, the framework provides a scalable and interpretable solution that can be integrated into modern Applicant Tracking Systems to improve recruitment efficiency. Future research may focus on supporting multilingual resumes, implementing dynamic scoring weights based on job roles, and integrating automated interview analysis modules to create a fully intelligent recruitment pipeline.
[1] Smith, T., Jones, M.: ‘Resume screening using natural language processing’, IET Systems Biology, 2022, 16, (4), pp. 210–218 [2] S. Bird, E. Klein, and E. Loper, Natural Language Processing with Python. O’Reilly Media, 2009. [3] J. Pennington, R. Socher, and C. Manning, “GloVe: Global vectors for word representation,” in Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, 2014, pp. 1532–1543. [4] L. Brown, H. Thomas, and C. James, “Artificial intelligence in recruitment systems,” IET Communications, vol. 15, no. 6, pp. 455–463, 2021. [5] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proceedings of NAACL-HLT, Minneapolis, USA, 2019, pp. 4171–4186. [6] T. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” in International Conference on Learning Representations (ICLR), 2013. [7] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” KDD, 2016. [8] Python Software Foundation.: ‘Python 3.13.2 documentation’, available at https://docs.python.org/3/, accessed January 2026 [9] GeeksforGeeks.: ‘Step-by-step guide to calculating RMSE using scikit-learn’, GeeksforGeeks, 2 November 2024, available at https://www.geeksforgeeks.org/step-by-step-guide-to-calculating-rmse-using-scikit-learn/, accessed January 2026 [10] Hugging Face.: ‘Hugging Face – The AI community building the future’, available at https://huggingface.co/, accessed January 2026
Publication Date
6/30/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
5
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...