AI-DRIVEN RESUME SKILL EXTRACTION AND JOB RECOMMENDATION SYSTEM USING HYBRID TRANSFORMER MAMBA MODEL
DOI: 
SHARE THIS ARTICLE
DOWNLOAD ARTICLE
REVIEW REPORT
CITE THIS ARTICLE
Manual resume screening is a time-consuming and error-prone process, particularly in large-scale recruitment where organizations receive hundreds of applications per job opening. Traditional Applicant Tracking Systems (ATS) primarily rely on rule-based keyword matching, which lacks contextual understanding and often leads to false positives and false negatives during candidate shortlisting. This paper presents an AI-driven Resume Skill Extraction and Job Recommendation System that integrates a custom-trained MAMBA Named Entity Recognition (NER) model with TF-IDvectorization and cosine similarity-based ranking. The proposed framework performs automated resume parsing, contextual skill identification, skill normalization, job-role similarity computation, and recommendation generation. Unlike conventional keyword-based systems, the MAMBA model captures contextual skill entities, improving extraction accuracy and adaptability to varied resume formats. Extracted skills are transformed into numerical vectors using TF-IDF weighting, and cosine similarity is computed between candidate profiles and predefined job role descriptions to determine relevance scores. Experimental evaluation demonstrates an estimated real-world F1-score of approximately 0.88, representing a significant improvement over traditional rule-based ATS systems while maintaining low computational overhead. The system executes efficiently on standard CPU hardware, making it suitable for small and medium-scale enterprise deployment. The proposed architecture offers a scalable, interpretable, and cost-effective solution for intelligent recruitment automation, balancing accuracy and computational efficiency.
Keywords
Article Information
Article Metrics
HOW TO CITE
Copy
S, B. A. (2026). AI-Driven Resume Skill Extraction and Job Recommendation System using Hybrid Transformer Mamba Model. International Journal of Science, Strategic Management and Technology, 02(04). https://doi.org/10.55041/ijsmt.v2i4.199
S, Bala. "AI-Driven Resume Skill Extraction and Job Recommendation System using Hybrid Transformer Mamba Model." International Journal of Science, Strategic Management and Technology, vol. 02, no. 04, 2026, pp. . doi:https://doi.org/10.55041/ijsmt.v2i4.199.
S, Bala. "AI-Driven Resume Skill Extraction and Job Recommendation System using Hybrid Transformer Mamba Model." International Journal of Science, Strategic Management and Technology 02, no. 04 (2026). https://doi.org/https://doi.org/10.55041/ijsmt.v2i4.199.
References
[2] M. Honnibal and I. Montani, "spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing," To appear, 2017. (Foundational citation for the custom SpaCy NER model used in the project architecture).
[3] B. Kinge, S. Mandhare, P. Chavan, and S. M. Chaware, "Resume screening using machine learning and NLP: A proposed system," International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2021.
[4] F. Pedregosa et al., "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825-2830, 2011. (Foundational citation for the TF-IDF vectorization and Cosine Similarity modules used in the project).
[5] P. K. Roy, S. S. Chowdhary, and R. Bhatia, "A Machine Learning approach for automation of Resume Recommendation system," Procedia Computer Science, vol. 167, pp. 2318-2327, 2020.
[6] S. Bird, E. Klein, and E. Loper, Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit. O'Reilly Media, Inc., 2009. (Foundational citation for the NLTK preprocessing pipeline, including tokenization and stopword removal).
[7] S. Lokesh, S. Mano Balaje, E. Prathish, and B. Bharathi, "Resume screening and recommendation system using machine learning approaches," Computer Science & Engineering: An International Journal (CSEIJ), 2021.
[8] L. Cabrera-Diego, B. Durette, M. Lafon, J.-M. Torres-Moreno, and M. El-Bèze, "Ranking resumes automatically using only resumes: A method free of job offers," Expert Systems with Applications, vol. 123, pp. 91-107, 2019.
[9] F. A. Jafari and R. Simon, "Automated Resume Screening System Using NLP and Machine Learning," International Journal of Scientific Research in Engineering and Management (IJSREM), vol. 09, no. 05, 2025.
[10] M. Saatçı, R. Kaya, and R. Ünlü, "Resume screening with natural language processing (NLP)," Alphanumeric Journal, 2021
Ethics and Compliance
Indexed In
Similar Articles
Previous Article
