Explainable AI for Fair and Transparent Human Resource Decision- Making

Human resource (HR) decisions are currently supported by algorithmic processes for hiring, promotions, and retaining employees, the lack of transparency in these models raises concerns about fairness, accountability, and trust of employees towards the process. In this paper, we develop a two-channel explainable artificial intelligence (XAI) model that combines the post hoc explanation methods such as SHAP and LIME with the inherently interpretable classifier for HR decisions. In our methodology, adversarial debiasing is used in the training process to prevent the influence of sensitive attributes on the model performance. For testing the effectiveness of the proposed XAI model, we conduct an experimental evaluation using IBM HR analytics dataset with three HR decision making tasks including promotion prediction, attrition prediction, and candidate selection task. As results, we show that our model achieves reductions in demographic parity disparity without compromising the explanation quality using local accuracy and stability measures. Comparing with baseline models in terms of fairness-utility trade-off consistently yields improvements.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-21
DOI
https://doi.org/10.5281/zenodo.24413084
Primary Topic
Explainable Artificial Intelligence (XAI)
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Explainable AI for Fair and Transparent Human Resource Decision- Making

Spoorthi R, K.Subhashini, Aishwarrya Prakash
Zenodo (CERN European Organization for Nuclear Research)
Explainable Artificial Intelligence (XAI)
article

Explainable AI for Fair and Transparent Human Resource Decision- Making

Spoorthi R, K.Subhashini, Aishwarrya Prakash
article en

Abstract

Human resource (HR) decisions are currently supported by algorithmic processes for hiring, promotions, and retaining employees, the lack of transparency in these models raises concerns about fairness, accountability, and trust of employees towards the process. In this paper, we develop a two-channel explainable artificial intelligence (XAI) model that combines the post hoc explanation methods such as SHAP and LIME with the inherently interpretable classifier for HR decisions. In our methodology, adversarial debiasing is used in the training process to prevent the influence of sensitive attributes on the model performance. For testing the effectiveness of the proposed XAI model, we conduct an experimental evaluation using IBM HR analytics dataset with three HR decision making tasks including promotion prediction, attrition prediction, and candidate selection task. As results, we show that our model achieves reductions in demographic parity disparity without compromising the explanation quality using local accuracy and stability measures. Comparing with baseline models in terms of fairness-utility trade-off consistently yields improvements.

Zenodo (CERN European Organization for Nuclear Research)
Explainable Artificial Intelligence (XAI)
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
Explainable AI for Fair and Transparent Human Resource Decision- Making — Spoorthi R, K.Subhashini, et al. · Zenodo (CERN European Organization for Nuclear Research) (2026) | TGRS Research Map | TGRS