×

Explainable AI For Fair And Transparent Human Resource Decision- Making

Author : Spoorthi R, K.Subhashini, Aishwarrya Prakash Journa Name: International Journal of Computational Research in Science and Technology Volume: 2 issue: 6 Year: Volume-2-issue-6 Views : 6
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.

Related Indexing Platform

Indexed

Leave Your Comment

Related Reviewers

Chat with Expert