Performance Appraisal Fairness, Perceived Organisational Support, Employee Engagement and Human Resource Analytics: A Human-Centred Decision-Support Framework
This study develops a human-centred human resource (HR) decision-support framework integrating performance appraisal fairness, perceived organisational support (POS), employee engagement and workforce analytics. Drawing on the Social Exchange Theory, the conceptual component proposes that appraisal fairness and POS are positively associated with employee engagement and that POS may strengthen the positive relationship between appraisal fairness and engagement. These relationships are proposed rather than empirically tested because the secondary dataset does not contain validated measures of appraisal fairness or POS. However, an “Engagement Score” is available; its measurement provenance is undocumented. Accordingly, the analytics case is used to examine the sufficiency and governance limitations of administrative HR records rather than to test the proposed conceptual relationships. The illustrative analytics component uses the publicly available HR Analytics Dataset. The raw file contained 3,150 records and 39 variables; removal of 150 exact duplicate records resulted in a final analytical dataset of 3,000 observations. A target-leakage audit identified ExitDate, EmployeeStatus, TerminationType, TerminationDescription and exit-dependent tenure measures as inappropriate prospective predictors. Following their exclusion, a leakage-controlled Random Forest (RF) model showed essentially chance-level discrimination, with an area under the receiver operating characteristic curve (ROC-AUC) of 0.507 and an area under the precision–recall curve (PR-AUC) of 0.528. Logistic regression produced similarly weak performance (ROC-AUC = 0.475). These findings demonstrate the importance of data provenance, temporal validity, leakage control, fairness assessment and human oversight when developing HR analytics systems. The study therefore contributes a theoretically grounded and systems-oriented framework for responsible workforce decision support while identifying direct empirical testing of the proposed moderation relationship as an important direction for future research.
Authors
- Nusrat Khan
Institutions
- Saudi Electronic University (SA)
Publication Details
- Journal
- Journal of Engineering Management and Systems Engineering
- Published
- 2026-11-16
- DOI
- https://doi.org/10.56578/jemse050406
- Primary Topic
- AI and HR Technologies
- Type
- article
- Field-Weighted Citation Impact
- 0.00