Pathakota Sri Chakrika Reddy, B.V.S. Tejaswi Harsha, Badisha Sai Ramya, : Prof. Ms. Roshni Solanki

DOI: https://doi.org/10.5281/zenodo.23240908

Contemporary recruitment systems suffer from severe friction between high-volume resume submissions and recruiter screening capacity. Conventional Applicant Tracking Systems (ATS) rely primarily on rigid exact-keyword matching heuristics, resulting in high false-rejection rates for qualified candidates who describe their technical competencies using synonymous or contextual phrasing. Conversely, candidates submit applications without diagnostic visibility into structural weaknesses or keyword deficits in their resumes. This paper presents the architecture, mathematical modeling, and empirical validation of AI-ATS, an intelligent recruitment platform integrating automated PDF text extraction, rule-weighted structural ATS scoring, high-dimensional vector-space job recommendation, and a synchronized dual-role recruitment workflow. AI-ATS parses raw binary resumes via pdfplumber, tokenizes technical skills using an optimized dictionary regex engine, and computes a piecewise ATS compatibility index across document length, skill density, and canonical structural sections. For candidate job matching, the system transforms candidate text and job descriptions into high-dimensional sparse Term Frequency-Inverse Document Frequency (TF-IDF) vectors and calculates cosine similarity across enterprise job profiles, returning ranked recommendations in under 320 ms. To bridge the candidate-recruiter gap, AI-ATS couples candidate-facing diagnostic filters with a recruiter portal supporting custom vacancy management, applicant tracking, and status progression. We formalize the candidate-job vector space model, present core algorithms for resume parsing, vector ranking, and candidate filtering, and analyze experimental results across multiple technical seniority profiles. We conclude by examining parsing edge cases, bias mitigation, and future integration with transformer-based embeddings

Applicant Tracking System, Natural Language Processing, Machine Learning, Information Retrieval, TF-IDF Vectorization, Cosine Recommendation, Similarity, Recruitment Interaction.

This paper presented the design, implementation, and empirical evaluation of AI-ATS, an intelligent, full-stack recruitment platform integrating automated PDF resume parsing, piecewise ATS compatibility scoring, TF-IDF vector-space job recommendations, and an synchronized candidate-recruiter management workflow. By coupling transparent diagnostic feedback for job seekers with dynamic vacancy management and applicant tracking for recruiters, AI-ATS resolves key bottlenecks that characterize conventional talent acquisition systems.

J. Chamorro-Premuzic, D. Winsborough, R. Sherman, and T. Hogan, "New talent signals: Shiny new objects or a revolution in talent identification?," Industrial and Organizational Psychology, vol. 9, no. 3, pp. 621–640, 2016.
[2] The Ladders, "Eye-Tracking Study: How Recruiters Really Review Resumes," Tech. Rep., Ladders Inc., New York, NY, 2018.
[3] P. Cappelli, "Making the approach to talent acquisition work," Harvard Business Review, vol. 97, no. 3, pp. 48–59, 2019.
[4] M. R. Frank, D. Autor, J. E. Bessen, et al., "Toward understanding the impact of artificial intelligence on labor," Proceedings of the National Academy of Sciences, vol. 116, no. 14, pp. 6531–6539, 2019.
[5] E. S. R. M. F. Silva, P. Cortez, and C. E. A. F. Santos, "Using text mining and machine learning to analyze job vacancies and resumes," Expert Systems with Applications, vol. 182, p. 115206, 2021.
[6] R. C. B. C. S. S. Roy, P. K. Singh, and M. D. Mahmud, "Automated Resume Screening System Using Natural Language Processing and Machine Learning," in Proc. IEEE Int. Conf. on Computing, Communication and Networking Technologies (ICCCNT), 2020, pp. 1 6.
[7] J. H. Park and S. C. Kim, "Spatial document parsing and layout analysis for semi-structured professional profiles," IEEE Access, vol. 9, pp. 142105–142116, 2021.
[8] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "BERT: Pre-training of deep bidirectional transformers for language understanding," in Proc. NAACL-HLT, Minneapolis, MN, 2019, pp. 4171–4186.
[9] G. Salton and C. Buckley, "Term-weighting approaches in automatic text retrieval," Information Processing & Management, vol. 24, no. 5, pp. 513–523, 1988.
[10] C. D. Manning, P. Raghavan, and H. Schütze, Introduction to Information Retrieval. Cambridge University Press, 2008.
[11] A. Singhal, "Modern information retrieval: A brief overview," IEEE Data Engineering Bulletin, vol. 24, no. 4, pp. 35–43, 2001.
[12] N. Reimers and I. Gurevych, "Sentence-BERT: Sentence embeddings using Siamese BERT-networks," in Proc. EMNLP-IJCNLP, Hong Kong, China, 2019, pp. 3982–3992.
[13] C. Qin, H. Zhu, T. Xu, C. Shen, E. Chen, and H. Xiong, "Enhancing Person-Job Fit for a Better Career: A Sequential Information Design," ACM Trans. on Information Systems (TOIS), vol. 38, no. 2, pp. 1–28, 2020.
[14] K. D. Hmieleski and J. C. Carr, "The impact of Applicant Tracking Systems on applicant perceptions and candidate withdrawal," Journal of Business and Psychology, vol. 35, no. 4, pp. 511–527, 2020.
[15] S. A. Hemamali and H. D. Bandara, "AI-driven talent acquisition: Transparent resume evaluation with explainable feedback," in Proc. IEEE Int. Conf. on Industrial and Information Systems (ICIIS), 2022, pp. 301–306.
[16] P. Tiwary, "FastAPI: Modern, High-Performance Web Framework for Python," Python Software Foundation, 2023. [Online]. Available: https://fastapi.tiangolo.com/
[17] F. Pedregosa et al., "Scikit-learn: Machine learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
[18] S. Bird, E. Klein, and E. Loper, Natural Language Processing with Python. O’Reilly Media, Inc., 2009

Pathakota Sri Chakrika Reddy, B.V.S. Tejaswi Harsha, Badisha Sai Ramya, : Prof. Ms. Roshni Solanki (2026). AI-ATS: A Scalable Machine Learning and Vector Space Model Platform for Automated Resume Screening and Contextual Job Recommendation. International Journal of Computer Science Engineering Techniques, 10(5), 240–246. ISSN: 2455-135X. DOI: https://doi.org/10.5281/zenodo.23240908