Fairness That Does Not Last: Auditing the Temporal Stability of Machine-Learning Fairness in Employee Promotion Prediction
DOI:
https://doi.org/10.66238/smsrj.v4i2.70Keywords:
algorithmic HRM, promotion prediction, algorithmic fairness, distribution shift, temporal stability, audit power, model monitoringAbstract
Machine-learning shortlisting is now common in promotion and succession processes, and good practice is to pre-declare a fairness bound and certify a model against it before release. This paper asks whether such a certificate survives contact with time, and separates two causes of failure. The first is statistical. The equal-opportunity difference (EOD) is estimated only on the promoted members of each group, so on a real public promotion benchmark of 54,808 employees and 4,668 historical promotions its standard error is 0.0753 for a 2,400-employee review cycle, one and a half times the 0.05 bound that is routinely declared, and about 21,800 reviewed employees are needed before a 95% interval becomes narrower than the bound itself. Across 200 re-splits of the same population with no drift at all, ROC-AUC has a coefficient of variation of 0.46% against 83.5% for |EOD|, validation and test EOD are uncorrelated (r = -0.05), and 21.4% of models that pass the pre-declared gate on validation violate it on an untouched test set. The second cause is drift. Replaying the real records as sequential promotion cycles under declared shift laws yields an exact oracle for the deployed model’s population fairness and shows that group-composition shift leaves parity intact, while within-group policy shift drives the true gap from 0.013 to 0.152 in ten cycles; sliding-window retraining with reweighting recovers 61% of that loss, whereas retraining alone can make parity worse. We propose TEMPOFAIR, an audit protocol that accumulates release evidence across cycles and that monitors a lower rather than an upper confidence bound at run time, cutting the false-alarm rate from 0.110 to 0.003 at 0.93 precision. We also report a negative result: no release-time gate, however conservative, anticipates drift. The instability reproduces on real calendar-time blocks of a second public benchmark. Code, results, and a reference-verification ledger are released.
References
1. Zhang, S. and Qiu, L. (2024). Data-driven assessment of pavement performance and resilience under extreme weather using the Long-Term Pavement Performance Program. AI and Data Science Journal, vol. 1, no. 1, pp. 57–66
2. Zhang, H. (2024). Graph-Aware Multi-Task Learning For Early Prediction Of Timing Violations And Routing Congestion In Digital Ic Physical Design. World Journal of Information Technology, 2(1): 13-20.
3. Wang, J., Tan, Y., Jiang, B., Wu, B., & Liu, W. (2025). Dynamic marketing uplift modeling: A symmetry-preserving framework integrating causal forests with deep reinforcement learning for personalized intervention strategies. Symmetry, 17(4), 610.
4. Zhao, X., Liu, J., Wang, Y., & Wang, J. (2026). CryptoMamba-SSM: Linear complexity state space models for cryptocurrency volatility prediction. IEEE Open Journal of the Computer Society, 7, 226-243.
5. Wang, J., Liu, J., Zheng, W., & Ge, Y. (2025). Temporal heterogeneous graph contrastive learning for fraud detection in credit card transactions. IEEE Access.
6. Sun, T., Yang, J., Li, J., Chen, J., Liu, M., Fan, L., & Wang, X. (2024). Enhancing auto insurance risk evaluation with transformer and SHAP. IEEE Access, 12, 116546-116557.
7. Zhang, H. (2025). Reinforcement Learning Approaches for Layout Optimization in Electronic Design Automation with Electromagnetic Compatibility Constraints. Frontiers in Robotics and Automation, 2(2), 77-93.
8. Han, X., Yang, Y., Chen, J., Wang, M., & Zhou, M. (2025). Symmetry-aware credit risk modeling: A deep learning framework exploiting financial data balance and invariance. Symmetry, 17(3), 341.
9. Chen, J., Cui, Y., Zhang, X., Yang, J., & Zhou, M. (2024). Temporal convolutional network for carbon tax projection: A data-driven approach. Applied Sciences, 14(20), 9213.
10. Sun, T., Wang, M., & Chen, J. (2025). Leveraging machine learning for tax fraud detection and risk scoring in corporate filings. Asian Business Research Journal, 10(11), 1-13.
11. Chen, J., Wang, M., & Sun, T. (2025). Intelligent tax systems and the role of natural language processing in regulatory interpretation. American Journal of Machine Learning, 6(4), 74-94.
12. Chen, Z., Liu, J., & Chen, J. (2025). Machine Learning Methods for Financial Forecasting in Enterprise Planning: Transitioning from Rule-Based Models to Predictive Analytics. Frontiers in Artificial Intelligence Research, 2(3), 541-564.
13. Chen, J., Liu, J., Liang, Y., & Zhou, M. (2026). KE-MLLM: A knowledge-enhanced multi-sensor learning framework for explainable fake review detection. Applied Sciences, 16(6), 2909.
14. Yue, X., Yang, J., & Liu, W. (2026). FraudDebate-Agent: A Multi-Agent LLM Framework with an Evidence-Based Debate Mechanism for Financial Statement Fraud Detection. Mathematics, 14(15), 2695.
15. Zhu, R. & Yue, X. (2024). An Explainable Machine Learning Framework For Predicting Dividend Sustainability And Financial Risk Of U.s. Reits Under Interest-Rate Shocks. Journal of Trends in Finance and Economics, 1(2): 48-57.
16. Yue, X. & Zhu, R. (2024). An Explainable Hybrid Machine Learning Framework For Cash-Flow-Conditioned Multi-Horizon Liquidity Risk Early Warning: An Sme-Oriented Benchmark Study. World Journal of Management Science, 2(1): 63-72.
17. Cui, Y., Han, X., Chen, J., Zhang, X., Yang, J., & Zhang, X. (2025). FraudGNN-RL: a graph neural network with reinforcement learning for adaptive financial fraud detection. IEEE Open Journal of the Computer Society, 6, 426-437.
18. Zi, B. (2024). Cloud-native distributed systems for real-time payment intelligence. AI and Data Science Journal, 1(1), 51-56.
19. Zhang, S. & Qiu, L. (2023). An Interpretable, Uncertainty-Aware Framework For Bridge Deterioration Prediction And Risk-Based Maintenance Prioritization. Academic Journal of Architecture and Civil Engineering, 1(2): 21-28.
20. Jin, J., Xing, S., Ji, E., & Liu, W. (2025). Xgate: explainable reinforcement learning for transparent and trustworthy api traffic management in iot sensor networks. Sensors, 25(7), 2183.
21. Xing, S., Wang, Y., & Liu, W. (2025). Multi-dimensional anomaly detection and fault localization in microservice architectures: A dual-channel deep learning approach with causal inference for intelligent sensing. Sensors, 25(11), 3396.
22. Xing, S., & Wang, Y. (2025). Proactive data placement in heterogeneous storage systems via predictive multi-objective reinforcement learning. IEEE Access, 13, 117986-117998.
23. Ji, E., Wang, Y., Xing, S., & Jin, J. (2025). Hierarchical reinforcement learning for energy-efficient API traffic optimization in large-scale advertising systems. IEEE Access.
24. Xing, S., & Wang, Y. (2025). Cross-modal attention networks for multi-modal anomaly detection in system software. IEEE Open Journal of the Computer Society.
25. Liu, Y., Ren, S., Wang, X., & Zhou, M. (2024). Temporal logical attention network for log-based anomaly detection in distributed systems. Sensors, 24(24), 7949.
26. Ren, S., Jin, J., Niu, G., & Liu, Y. (2025). ARCS: Adaptive reinforcement learning framework for automated cybersecurity incident response strategy optimization. Applied Sciences, 15(2), 951.
27. Li, P., Ren, S., Zhang, Q., Wang, X., & Liu, Y. (2024). Think4SCND: Reinforcement learning with thinking model for dynamic supply chain network design. IEEE Access, 12, 195974-195985.
28. Hu, X., Zhao, X., Wang, J., & Yang, Y. (2025). Information-theoretic multi-scale geometric pre-training for enhanced molecular property prediction. Plos one, 20(10), e0332640.
29. Wang, M., Zhang, X., Yang, Y., & Wang, J. (2025). Explainable machine learning in risk management: Balancing accuracy and interpretability. Journal of Financial Risk Management, 14(3), 185-198.
30. Yang, J., Li, P., Cui, Y., Han, X., & Zhou, M. (2025). Multi-sensor temporal fusion transformer for stock performance prediction: An adaptive Sharpe ratio approach. Sensors, 25(3), 976.
31. Zhao, X., Sun, T., Ren, S., Yang, J., & Liu, Y. (2025). RAG-Based AI Agents for Enterprise Software Development: Implementation Patterns and Production Deployment. Frontiers in Artificial Intelligence Research, 2(3), 501-520.
32. Sun, T., Wang, M., & Chen, J. (2025). Leveraging machine learning for tax fraud detection and risk scoring in corporate filings. Asian Business Research Journal, 10(11), 1-13.
33. Bian, M., Li, P., Lin, Y., Wang, Y., & Teng, D. (2026). Assessing Green Public Supply Chains Resilience under Carbon Neutrality Goals: A Multi-Agent Reinforcement Learning Framework. IEEE Access.
34. Shang, W., Teng, D., Chen, T., Zhang, F., & Ding, J. (2026). Neuro-Elastic: A Unified Framework for Hardware-Aware Adaptive Quantization and Dynamic Sparsity in Real-Time Edge Intent Prediction. IEEE Access.
35. Teng, D. (2025). TEAS: Token-and energy-aware autoscaling for cost-efficient LLM serving. AI and Data Science Journal, 6(3), 1-10.
36. Rhee, M., Zou, J., Mo, T., Teng, D., & Yang, J. S. (2026). Enhancing web search agents with self-play contrastive fine-tuning. IEEE Access.
37. Wang, B., Zhao, W., & Wang, Z. (2024). Das-Gnn: A Scalable Disagreement-Aware Graph Neural Framework For Anomaly Detection In Large-Scale Networks. AI and Data Science Journal, 1(1): 67-75.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Haruto Nakamura, Yuki Tanaka
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles in the Social and Management Sciences Research Journal are published under the Creative Commons Attribution 4.0 (CC BY 4.0) license. Users can share, copy, distribute, and adapt the work, including for commercial purposes, provided proper attribution is given to the authors and the journal.
