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

Institutions

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
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Performance Appraisal Fairness, Perceived Organisational Support, Employee Engagement and Human Resource Analytics: A Human-Centred Decision-Support Framework

Nusrat Khan
3 links
Journal of Engineering Management and Systems Engineering
AI and HR Technologies
article

Performance Appraisal Fairness, Perceived Organisational Support, Employee Engagement and Human Resource Analytics: A Human-Centred Decision-Support Framework

Nusrat Khan
article en

Abstract

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.

Journal of Engineering Management and Systems EngineeringVol. 5(4)
Saudi Electronic University (SA)
Decent work and economic growth
AI and HR Technologies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon