Approaches to Scaling Skill Intelligence Platforms
DOI:
https://doi.org/10.47941/hrlj.3446Keywords:
Skills-Based Hr, Kill Intelligence Platforms, Skill Extraction, Ontology Alignment, Esco/O*Net, Knowledge Graphs, Large Language Models (LLMs)Abstract
Purpose: Skill Intelligence Platform (SIP) Support for hiring skills, mobility and learning. This conceptual document synthesizes empirical conclusions to identify SIP scalable and responsible approaches.
Methodology: We have made an integrated overview of fifteen sources with skill extraction, oncology leveling, knowledge of knowledge and operation results. Studies have been carried out for HR relevance and clear data report, matrix and references. The evidence was coded on the map of evidence regarding data sources, algorithms, oncology, evaluation and life cycle control.
Findings: Synthesis created five -emental structure (skill -5): Source integration, knowledge modeling, pipe estimates, life cycle engineering and logic and management. During a study, a hybrid pipe increases the pipeline combining weak supervision with large language models without losing accuracy. Improved portability ESCO/O*improved. The job skill chart allows comparison, mobility and course design. The Lups controls check including the shadow test, Canary and drift monitors. The main risks included distortion, whirling of the concept, drift of tongue and cost instability, Human loop drugs, audit trails and budget route reduced them.
Unique Contribution to Theory, Practice and Policy: This study advances theory by transferring oncology-derived cumulative uncertainty modelling (CUM) and modular hybrid estimation into the HR analytics domain, improves practice by providing a scalable and disciplined framework for evaluating strategic intervention programmes (SIP) against measurable business outcomes, and informs policy by recommending standardized research intervals, multilingual benchmarking, automated evidence updates, and mandatory distortion audits to align analytical models with real workforce effects.
Downloads
References
Chiarello, F., Fantoni, G., Hogarth, T., Giordano, V., Baltina, L., & Spada, I. (2021).
Towards ESCO 4.0: Is the European classification of skills in line with Industry 4.0? A text mining approach. Technological Forecasting and Social Change, 173, 121177. https://doi.org/10.1016/j.techfore.2021.121177
Decorte, J.-J., Van Hautte, J., Deleu, J., Develder, C., & Demeester, T. (2022). Design of negative sampling strategies for distantly supervised skill extraction. In Proceedings of the RecSys in HR 2022 Workshop (CEUR Workshop Proceedings, Vol. 3218). https://ceur-ws.org/Vol-3218/RecSysHR2022-paper_4.pdf
de Groot, M., Verberne, S., & Arendsen, R. (2021). Job posting-enriched knowledge graph for skills-based education and job matching. arXiv. https://arxiv.org/pdf/2109.02554
Gavrilescu, M., Dinsoreanu, M., & Rădulescu, C. (2025). Techniques for transversal skill classification and extraction based on ESCO using AI. Information, 16(3), 167. https://www.mdpi.com/2078-2489/16/3/167
Howison, M., Ensor, W. O., Paden, M., & Walker, K. (2024). Extracting structured labor market information from job postings using generative AI. Digital Government: Research and Practice. https://doi.org/10.1145/3674847
Nguyen, K. C., Zhang, M., Montariol, S., & Bosselut, A. (2024). Rethinking skill extraction in the job market domain using large language models. In Proceedings of the 1st Workshop on NLP for Human Resources (NLP4HR 2024). Association for Computational Linguistics. https://aclanthology.org/2024.nlp4hr-1.3.pdf
OECD. (2024). Artificial intelligence and the changing demand for skills in the labour market. OECD Publishing. https://www.oecd-ilibrary.org/education/artificial-intelligence-and-the-changing-demand-for-skills-in-the-labour-market_2a240956-en
Ortega-Flores, I., Casado-Lumbreras, C., Colomo-Palacios, R., & Soto-Aguirre, M. (2022). Using LinkedIn endorsements to reinforce an ontology and ML-based recommender system to improve professional skills. Electronics, 11(8), 1190. https://www.mdpi.com/2079-9292/11/8/1190
Rosenberger, J. S., Canzani, E., Marcon, L., Baeza-Yates, R., & Gionis, A. (2025). CareerBERT: Matching résumés to ESCO jobs in a shared embedding space. Expert Systems with Applications. Advance online publication. https://www.sciencedirect.com/science/article/pii/S0957417425006657
Seif, A., Fadel, M., El Bassuony, A., & El-Beltagy, S. (2024). A dynamic jobs-skills knowledge graph. In Proceedings of the RecSys in HR 2024 Workshop (CEUR Workshop Proceedings, Vol. 3788). https://ceur-ws.org/Vol-3788/RecSysHR2024-paper_1.pdf
Senger, E., Zhang, M., van der Goot, R., & Plank, B. (2024). A survey on skill extraction and classification from job postings. In Proceedings of the 1st Workshop on NLP for Human Resources (NLP4HR 2024). Association for Computational Linguistics. https://aclanthology.org/2024.nlp4hr-1.1.pdf
Shi, B., Yang, J., Guo, F., & He, Q. (2020). Salience and market-aware skill extraction for job targeting. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 2954–2964). https://doi.org/10.1145/3394486.3403338
Vrolijk, J., Rebelo, P., Beijer, H., & van der Meer, R. (2024). Ontology learning for ESCO: Leveraging LLMs to navigate the skills graph. In Joint Ontology Workshops 2024 (CEUR Workshop Proceedings). http://ceur-ws.org/Vol-3829/short3.pdf
Zhang, M., Jensen, K. N., Sonniks, S. D., & Plank, B. (2022). SkillSpan: Hard and soft skill extraction from English job postings. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022). https://aclanthology.org/2022.naacl-main.366.pdf
Zhang, M., Jensen, K. N., van der Goot, R., & Plank, B. (2022). Skill extraction from job postings using weak supervision. In Proceedings of the RecSys in HR 2022 Workshop (CEUR Workshop Proceedings, Vol. 3218). https://vbn.aau.dk/files/662796103/RecSysHR2022_paper_10.pdf
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Syrotenko Viktoriia
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution (CC-BY) 4.0 License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
