Объяснимый искусственный интеллект в кадровой аналитике: анализ факторов производительности

Александр Николаевич Козинец

Authors

Aliaksandr N. Kazinets Belarusian State University of Informatics and Radioelectronics, 6 P. Browki Street, Minsk 220013, Belarus

Keywords:

human resource analytics, explainable artificial intelligence, transversal skills, digital competencies, gradient boosting, SHAP method, employee performance, key performance indicators, KPIs

Abstract

In the context of digitalisation and the growing importance of human capital, explainable artificial intelligence models in human resource analytics are particularly relevant. Using the XGBoost gradient model, the impact of transversal skills and digital competencies on key employee performance indicators is analysed. The SHAP method, which ensures forecast transparency, is used to interpret the contribution of features. A methodology is developed for the stages of open data selection, feature generation, and model interpretation. It is established that factors such as communication skills, digital literacy, and tenure have a significant impact on performance. The managerial consequences of using explainable artificial intelligence to support human resource development decisions are discussed. The importance of interpretable models for increasing trust in algorithms in human resource analytics is emphasised.

Author Biography

Aliaksandr N. Kazinets, Belarusian State University of Informatics and Radioelectronics, 6 P. Browki Street, Minsk 220013, Belarus

postgraduate student at the department of economics, faculty of engineering and economics

References

Becker GS. Human capital: a theoretical and empirical analysis. Chicago: University of Chicago Press; 1964. 187 p.
Флек МБ, Угнич ЕА. Разработка модели цифровых компетенций работников в условиях цифровой трансформации предприятия. Перспективы науки и образования. 2023;3:706–723. DOI: 10.32744/pse.2023.3.43.
Ribeiro MT, Singh S, Guestrin C. Why should I trust you? Explaining the predictions of any classifier. In: Balaji Krishnapuram, Mohak Shah, editors. Proceedings of the 22nd ACM SIGKDD International conference on knowledge discovery and data mining; 13–17 August 2016; San Francisco, USA. New York: Association for Computing Machinery; 2016. p. 1135–1144.
Arrieta AB, Díaz-Rodríguez N, Ser JD, Bennetot A, Tabik S, González AB, et al. Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges. Information Fusion. 2020;58:82–115. DOI: 10.1016/j.inffus.2019.12.012.
Lee JY, Lee Y. Integrative literature review on people analytics and implications from the perspective of human resource development. Human Resource Development Review. 2024;23(1):58–87.
Pinto GBS, Mello CE, Garcia ACB. Explainable AI in labor‑market applications. In: Rocha AP, Steels L, van den Herik JH, editors. Proceedings of the 17th International conference on agents and artificial intelligence; 2025 February 23–25; Porto, Portugal. Volume 3. Lissabon: Science and Technology Publications; 2025. p. 1450–1457. DOI: 10.5220/0013384100003890.
Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. In: von Luxburg U, Guyon I, Bengio S, Wallach H, Fergus R, editors. Proceedings of the 31st International conference on neural information processing systems; 2017 December 4–9; Long Beach, USA. Volume 30. New York: Curran Associates; 2017. p. 4765–4774.
Chaturvedi S, Chaturvedi R. Who gets the callback? Generative AI and gender bias. arXiv:2504.21400 [Preprint]. 2025 [cited 2025 May 3]. Available from: https://arxiv.org/abs/2504.21400.
Klöpper M, Messer U. Hiding behind algorithms: people analytics and perceived fairness violation in managerial decisions [Internet]. In: Avital M, Karahanna E, Themistocleous M, editors. Proceedings of the 32nd European conference on information systems. People first: constructing digital futures together; 2024 June 13–19; Paphos, Cyprus [cited 2025 May 3]. Available from: https://aisel.aisnet.org/ecis2024/track07_busanalytics/track07_busanalytics/16.
Chen T, Guestrin C. XGBoost: a scalable tree‑boosting system. In: Krishnapuram B, Shah M, editors. KDD’16. Proceedings of the 22nd ACM SIGKDD International conference on knowledge discovery and data mining; 2016 August 13–17; San Francisco, USA. New York: Association for Computing Machinery; 2016. p. 785–794. DOI: 10.1145/2939672.2939785.
Akiba T, Sano S, Yanase T, Ohta T, Koyama M. Optuna: a next‑generation hyperparameter optimization framework. In: Teredesai A, Kumar V, editors. KDD’19. Proceedings of the 25th ACM SIGKDD International conference on knowledge discovery & data mining; 2019 August 4–8; Anchorage, USA. New York: Association for Computing Machinery; 2019. p. 2623–2631. DOI: 10.1145/3292500.3330701.
Spence AM. Job market signaling. Cambridge: Harvard University Press; 1973. 174 p.
Mincer J. Schooling, experience, and earnings. Cambridge: National Bureau of Economic Research; 1974. 152 p.
Гуриева СД. Феномен «тяни-выталкивай» как проявление гендерного неравенства в организационном контексте. Russian Journal of Education and Psychology. 2020;11(4):7–11. EDN: NWCLHP.