Karunarathne, Lakmali 
ORCID: https://orcid.org/0009-0000-7720-7817, Ganesan, Swathi ORCID: https://orcid.org/0000-0002-6278-2090, Somasiri, Nalinda ORCID: https://orcid.org/0000-0001-6311-2251 and Karunarathne, Kavindu
(2026)
Employee Productivity Analytics and Prediction: A Dynamic Productivity and Burnout Modelling Engine (DPBME) for Privacy-Aware Workforce Analytics.
Recent Research Reviews Journal, 5 (2).
pp. 355-378.
Preview |
Text
Employee_Productivity_Analytics_and_Prediction__A_Dynamic_Productivity_and_Burnout_Modelling_Engine_.pdf - Published Version Available under License Creative Commons Attribution Non-commercial. | Preview |
Abstract
Digital collaboration tools and project management systems provide continuous data about workforce behavior and activities. Conventional workforce analytics are mainly concerned with historical performance and turnover of employees, with no predictive abilities with respect to future productivity or signs of burnout. In this paper, we propose the Dynamic Productivity and Burnout Modelling Engine (DPBME) that combines the productivity model, designation cohort decline index, and burnout risk score while maintaining explainability and privacy principles. Tested on the dataset of 35,000 employee records, Ridge Regression, Random Forest, and Gradient Boosting Machine (GBM) algorithms are evaluated, with GBM being the most effective one (R² = 0.9072). The obtained burnout risk score corresponds well to the real Burn Rate (Pearson r = 0.6562). The sensitivity analysis demonstrates stable parameters' values for the risk of burnout, while the SHAP analysis revealed the importance of mental fatigue and workload as predictors of productivity. The results are presented associatively and cover limitations, governance, and privacy aspects in accordance with the GDPR Article 22 standards.
| Item Type: | Article |
|---|---|
| Status: | Published |
| DOI: | 10.36548/rrrj.2026.2.007 |
| Subjects: | Q Science > Q Science (General) > Q325 Machine learning Q Science > QA Mathematics > QA76 Computer software Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4450 Databases |
| School/Department: | London Campus |
| URI: | https://ray.yorksj.ac.uk/id/eprint/15817 |
University Staff: Request a correction | RaY Editors: Update this record
Altmetric
Altmetric
