An Employee Performance Prediction Model Based on Artificial Intelligence and Multi-Source Data
International Journal of e-Collaboration · 21.10.2026 · 22 (1) · 1-40
DOI: 10.4018/ijec.425376 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of e-Collaboration, erschienen am 21.10.2026. Verfasst von Shihui Wang. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0).
Abstract (Originalsprache)
This research aimed to develop an employee performance prediction model based on artificial intelligence and multi-source data using a novel dynamic vortex algorithm-mutated random gradient boosting model. Data normalization was conducted using Z-score scaling, and class imbalance was mitigated using the synthetic minority oversampling technique. Principal component analysis was employed to reduce dimensionality and retain performance-informative attributes. The model was implemented using Python-based machine learning libraries. The reported results demonstrated strong internal performance on the selected “Employee Multi-Source Performance Dataset,” but they did not establish universal applicability across different organizations, industries, or human resources systems. Experimental evaluation demonstrated a strong performance with an accuracy of 0.9889, a precision of 0.9675, a specificity of 0.9918, and an F-measure of 0.9691, compared to conventional ensemble models across multiple performance parameters.
Zitieren
APA
Wang, S. (2026). An Employee Performance Prediction Model Based on Artificial Intelligence and Multi-Source Data. International Journal of e-Collaboration, 22(1), 1-40. https://doi.org/10.4018/ijec.425376
Vancouver
Wang S. An Employee Performance Prediction Model Based on Artificial Intelligence and Multi-Source Data. International Journal of e-Collaboration. 2026;22(1):1-40. doi:10.4018/ijec.425376
BibTeX
@article{Wang2026,
author = {Wang, Shihui},
title = {An Employee Performance Prediction Model Based on Artificial Intelligence and Multi-Source Data},
journal = {International Journal of e-Collaboration},
year = {2026},
volume = {22},
number = {1},
pages = {1--40},
doi = {10.4018/ijec.425376}
}
EUVIMED