Data-Driven Approach in HR-Engineering in the Context of Personnel Turnover Management

Abstract

Background: High employee turnover imposes severe operational and financial costs on modern enterprises. In volatile labor markets, traditional reactive human resource management fails to anticipate workforce attrition before human capital depletion occurs.

Objective: This study develops and evaluates an interpretable predictive decision-support framework using gradient boosting algorithms (XGBoost and CatBoost) to forecast voluntary employee turnover risk.

Methods: Using an open secondary HR analytics benchmark dataset (N = 14,999) encompassing performance metrics, working hours, project loads, tenure, and compensation levels, continuous probabilistic risk scoring models were trained and calibrated. Performance was evaluated on a 70/30 train-test split using MAE, MSE, RMSE, and R² metrics alongside kernel density estimation (KDE) feature analysis.

Results: Both gradient boosting models achieved high accuracy on unseen test data, with CatBoost (R² = 0.9359, MAE = 0.0392, RMSE = 0.1078) demonstrating slightly superior calibration and explanatory power compared to XGBoost (R² = 0.9305, MAE = 0.0436, RMSE = 0.1123). Non-linear distributions revealed that extreme monthly working hours, project overload or underload, and depleted job satisfaction constitute key risk indicators.

Conclusion: Embedding continuous risk scoring into organizational dashboards enables management to transition from reactive exit interviews to proactive talent retention, providing a scalable decision-support architecture for contemporary business informatics.

A Blockchain Platform for Vaccine Beneficiary Registration, Side Effects, Cold Supply Chain, and Personnel Training and Employment Management
Sensors (Basel, Switzerland)1 Oct 2026Peer-reviewedCC BYFull textEurope PMC
Chinese science popularization guideline on the prevention and management of sacrococcygeal pilonidal sinus (2026, medical personnel edition)
Medical Science Popularization Branch of the Chinese Medical Doctor Association, Anorectal Surgeons Branch of the Chinese Medical Doctor Association, Anorectal Science Popularization Group of the Medical Science Popularization Branch of the Chinese Medical Doctor Association
结直肠肛门外科1 Aug 2026Peer-reviewedCC BY-NC-NDFull textSurgery & anaesthesiaDOAJ
Rabies in Military Personnel: Epidemiology, Clinical Challenges, and Strategies for Prevention and Management
Elodie Monchatre-Leroy, Diana Isabela Costescu Strachinaru, Oula Itani +3
Tropical Medicine and Infectious Disease26 Aug 2026Peer-reviewedCC BY 4.0Full textMicrobiologyHAL
Chinese science popularization guideline on the prevention and management of chronic constipation (2026, medical personnel edition)
Medical Science Popularization Branch of the Chinese Medical Doctor Association, Anorectal Surgeons Branch of the Chinese Medical Doctor Association, Anorectal Science Popularization Group of the Medical Science Popularization Branch of the Chinese Medical Doctor Association
结直肠肛门外科1 Aug 2026Peer-reviewedCC BY-NC-NDFull textSurgery & anaesthesiaDOAJ
Working conditions, security and grievance management among Bundibugyo virus response personnel: exploratory findings from an anonymous survey in eastern Democratic Republic of the Congo
J. G. L. Verheyden, C. N. Mudogo
medRxiv8 Sep 2026PreprintCC BY-NC-NDFull textEpidemiology & public healthmedRxiv

Cite

BibTeX RIS

BibTeX

@misc{vedernikov2026datadriven,
  title = {{Data-Driven Approach in HR-Engineering in the Context of Personnel Turnover Management}},
  author = {Mykhailo Vedernikov and Oksana Chernushkina and Lesia Volianska-Savchuk and Natalia Bazaliyska and Yeva Bohdanova and Mariya Zelena and Tetyana Furman},
  howpublished = {Zenodo},
  year = {2026},
  month = oct,
  doi = {10.5281/zenodo.23668985},
  url = {https://zenodo.org/records/23668985},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Data-Driven Approach in HR-Engineering in the Context of Personnel Turnover Management
AU  - Mykhailo Vedernikov
AU  - Oksana Chernushkina
AU  - Lesia Volianska-Savchuk
AU  - Natalia Bazaliyska
AU  - Yeva Bohdanova
AU  - Mariya Zelena
AU  - Tetyana Furman
PY  - 2026
DA  - 2026/10/26
PB  - Zenodo
DO  - 10.5281/zenodo.23668985
UR  - https://zenodo.org/records/23668985
AB  - Background: High employee turnover imposes severe operational and financial costs on modern enterprises. In volatile labor markets, traditional reactive human resource management fails to anticipate workforce attrition before human capital depletion occurs.  Objective: This study develops and evaluates an interpretable predictive decision-support framework using gradient boosting algorithms (XGBoost and CatBoost) to forecast voluntary employee turnover risk.  Methods: Using an open secondary HR analytics benchmark dataset (N = 14,999) encompassing performance metrics, working hours, project loads, tenure, and compensation levels, continuous probabilistic risk scoring models were trained and calibrated. Performance was evaluated on a 70/30 train-test split using MAE, MSE, RMSE, and R&sup2; metrics alongside kernel density estimation (KDE) feature analysis.  Results: Both gradient boosting models achieved high accuracy on unseen test data, with CatBoost (R&sup2; = 0.9359, MAE = 0.0392, RMSE = 0.1078) demonstrating slightly superior calibration and explanatory power compared to XGBoost (R&sup2; = 0.9305, MAE = 0.0436, RMSE = 0.1123). Non-linear distributions revealed that extreme monthly working hours, project overload or underload, and depleted job satisfaction constitute key risk indicators.  Conclusion: Embedding continuous risk scoring into organizational dashboards enables management to transition from reactive exit interviews to proactive talent retention, providing a scalable decision-support architecture for contemporary business informatics.
ER  -

Abstract

Related

Cite