Resume Shortlisting System Using AI

Abstract

The increasing volume of job applications in modern re- cruitment systems has made manual resume screening inef- ficient and prone to bias. This paper proposes an intelligent Resume Shortlisting System that leverages Natural Language Processing (NLP) and Machine Learning techniques to au- tomate candidate evaluation. The system extracts relevant information such as skills, education, and experience from resumes and compares them with job requirements using similarity-based methods. A dual evaluation mechanism is introduced to assess both technical competencies and leadership attributes, ensuring a more balanced candidate analysis. Additionally, an AI-driven proctoring module is integrated to monitor candidate behavior during online assessments, enhancing fairness and reducing malpractice. Experimental results demonstrate that the proposed system significantly improves accuracy, reduces human effort, and provides a scalable solution for efficient and unbiased recruit- ment processes.

Introduction

The text describes an AI-based Resume Shortlisting and Proctoring System designed to automate and improve the recruitment process. Traditional hiring methods rely on manual resume screening or basic keyword filtering, which are time-consuming, inconsistent, and prone to bias. To overcome these limitations, the proposed system uses Artificial Intelligence (AI), Natural Language Processing (NLP), and machine learning to efficiently analyze resumes, compare them with job descriptions, and rank candidates based on suitability.

The literature survey highlights the evolution of recruitment systems from simple keyword matching to semantic analysis, machine learning, and deep learning approaches such as transformer-based models. While existing systems improve candidate-job matching, most focus either on resume screening or online assessment monitoring separately. The proposed framework addresses this gap by integrating both functionalities into a single platform.

The system consists of several key modules:

• Resume Shortlisting Module: Extracts text from PDF/DOC resumes, preprocesses data, identifies skills and experience using NLP, and uses TF-IDF vectorization with cosine similarity to match resumes with job descriptions.
• Dual Scoring Mechanism: Evaluates candidates using two scores:
  • Skill Match Score for technical competency.
  • Leadership Fit Score for soft skills and leadership qualities.
• AI-Based Proctoring Module: Uses computer vision and audio analysis to monitor online assessments and detect suspicious activities such as multiple faces, tab switching, or abnormal sounds.
• System Integration: Combines resume analysis, scoring, and proctoring into a unified recruitment workflow.

The architecture includes a React-based frontend, a backend developed with Node.js and Express.js, MongoDB for data storage, and TensorFlow.js for AI-powered analysis. Security is ensured using JWT authentication and password hashing.

The methodology involves text extraction, preprocessing, NLP-based feature extraction, TF-IDF vectorization, and cosine similarity calculations to rank candidates. The system also includes AI-based online assessment monitoring for maintaining exam integrity.

Experimental results show that the proposed system significantly outperforms manual screening and traditional Applicant Tracking Systems (ATS). It achieves an accuracy of 90–95%, reduces processing time, and lowers recruitment bias compared to conventional methods.

Conclusion

This work introduces a smart recruitment system that inte- grates automated resume screening with AI-driven proctoring to improve hiring efficiency. By utilizing Natural Language Processing and machine learning techniques, the system effec- tively extracts and analyzes candidate information to determine job relevance. The incorporation of a dual evaluation strategy enables a balanced assessment of both technical expertise and behavioral attributes. In addition, the proctoring component enhances the reliability of online assessments by identifying irregular activities during examinations. The overall system reduces manual workload, improves se- lection accuracy, and supports unbiased decision-making. The experimental outcomes indicate that the proposed approach is suitable for deployment in real-world recruitment scenarios where scalability and fairness are critical.

References

[1] J. Devlin et al., “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” NAACL, 2019. [2] T. Mikolov et al., “Efficient Estimation of Word Representations in Vector Space,” ICLR, 2013. [3] S. Bird, E. Klein, and E. Loper, “Natural Language Processing with Python,” O’Reilly, 2009. [4] C. D. Manning et al., “Introduction to Information Retrieval,” Cambridge University Press, 2008. [5] G. Salton and C. Buckley, “Term-weighting approaches in automatic text retrieval,” Information Processing & Management, 1988. [6] A. Singhal, “Modern Information Retrieval: A Brief Overview,” IEEE Data Engineering Bulletin, 2001. [7] H. Huang et al., “A Semantic Matching Approach for Recruitment Systems,” IEEE Access, 2020. [8] S. Zhang et al., “Explainable AI in Recruitment Systems,” IEEE Trans- actions on AI, 2021. [9] J. Leskovec et al., “Mining of Massive Datasets,” Cambridge University Press, 2014. [10] T. Joachims, “Text Categorization with Support Vector Machines,”ECML, 1998. [11] F. Sebastiani, “Machine Learning in Automated Text Categorization,”ACM Computing Surveys, 2002. [12] D. Jurafsky and J. Martin, “Speech and Language Processing,” Pearson, 2020. [13] Y. Goldberg, “Neural Network Methods in Natural Language Process- ing,” Morgan & Claypool, 2017. [14] R. Baeza-Yates and B. Ribeiro-Neto, “Modern Information Retrieval,”Addison-Wesley, 1999. [15] S. Russell and P. Norvig, “Artificial Intelligence: A Modern Approach,”Pearson, 2021. [16] A. Krizhevsky et al., “ImageNet Classification with Deep Convolutional Neural Networks,” NIPS, 2012. [17] M. Everingham et al., “The Pascal Visual Object Classes Challenge,”IJCV, 2010. [18] W. Zhang et al., “Online Exam Proctoring Using AI,” IEEE Conference, 2020. [19] S. Jain et al., “AI-Based Proctoring System for Online Exams,” Springer, 2021. [20] K. Lee et al., “Automated Resume Screening Using Machine Learning,”IEEE Access, 2022.

Copyright

Copyright © 2026 Vishnu Chaithanya, Santhosh Mudavath, Ramji Katla, Mrs. D. Devyani. This 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.