چکیده مقاله
Administrative justice plays a vital role in maintaining equity and trust within public education systems However, implicit biases and discriminatory patterns often distort fairness in human resource management This study introduces a hybrid XGBoost–Deep Neural Network DNN model for detecting administrative discrimination in educational institutions Using a dataset of 12,480 administrative decisions from regional education departments, the proposed model achieved 94 6% accuracy, outperforming baseline algorithms by 8 7% Statistical validation p < 0 01, 95% CI confirms the model’s robustness and generalizability across diverse demographic and organizational variables Feature importance analysis identified seniority 34% , gender 27% , and institutional hierarchy 19% as dominant fairness factors The model’s interpretability, ensured through SHAP and LIME frameworks, enables transparent auditing of administrative decisions This research provides a practical foundation for deploying AI driven fairness analytics in public sector management and policy making, fostering equity, accountability, and trust in educational administration
کلیدواژهها
نویسندگان
Babak Ghafari
Department of Computer Engineering, Ma C , Islamic Azad University, Mashhad, Iran
Yalda Kheirkhah
Department of Computer Engineering, Ma C , Islamic Azad University, Mashhad, Iran
Zahra Sadritabatabaie
Vocational Instructor, Region ۷, Department of Education, Mashhad, Iran
شیوه ارجاع
Ghafari, Babak and Kheirkhah, Yalda and Sadritabatabaie, Zahra,1404,Algorithmic Justice in Education Hybrid XGBoost–DNN for Real-Time Detection and Fairness Optimization in HR Decision-Making,1th national conference on challenges of human capital management in large scale organizations,Mashhad
ارائهشده در
مجموعه مقالات اولین کنفرانس ملی چالش های مدیریت سرمایه انسانی در سازمان های بزرگ مقیاس23 مهر 1404 · مشهد