Intelligent Resume Screening from Resumes Using Hybrid Machine Learning Models

DOI

10.2991/978-94-6239-697-5_35How to use a DOI?

Keywords

Resume screening; Term Frequency-Inverse Document Frequency; SBERT embeddings; Stacked ensemble model; Semantic similarity

Abstract

The conventional approaches to job hiring suffered from biased, inaccurate, and time-consuming due to the dramatic growth of resumes. In general, current Auto-Matcher systems are based on single learning model to extract shallow linguistic features, which cannot represent multidimension information of resumes effectively. To overcome this weakness, we put forward a hybrid ML framework for deep extraction of statistical and semantic representations from resumes with TFIDF, LCR and SBERT embeddings. A novel ensemble stacked system that integrates Bi-directional Long Short-Term Memory (BiLSTM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) classifiers based on Logistic Regression (LR) is proposed to permit more accurate and contextually relevant classification. The stacked model LR achieved 99% accuracy, with a precision of 0.985, recall of 0.99, and F1-score of 0.98 in testing with a benchmark dataset of 13,389 resumes. The SBERT similarity scores recorded up to 0.89 for Human Resources (HR) roles, signalling effective role-specific semantic alignment and high certainty in the classification suitability predictions of the stacked model (between 96.62% - 99.16%). Therefore, the current research provides a significant advancement in resume screening that is scalable to a system that offers an unbiased, semantically enhanced, intelligent automation of recruitment.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Prabhjot Kaur
AU  - Jasmeen Gill
AU  - Harmandeep Singh Gill
PY  - 2026
DA  - 2026/06/04
TI  - Intelligent Resume Screening from Resumes Using Hybrid Machine Learning Models
BT  - Proceedings of the Conference on Bridging Engineering Disciplines with AI and Machine Learning (BEDAIML 2026)
PB  - Atlantis Press
SP  - 424
EP  - 443
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-697-5_35
DO  - 10.2991/978-94-6239-697-5_35
ID  - Kaur2026
ER  -