Algorithmic Bias Under the EU AI Act: Compliance Risk, Capital Strain, and Pricing Distortions in Life and Health Insurance Underwriting

Siddharth Mahajan (), Rohan Agarwal and Mihir Gupta
Additional contact information
Siddharth Mahajan: Cantor Research Institute, Blauvelt, NY 10913, USA
Rohan Agarwal: Cantor Research Institute, Blauvelt, NY 10913, USA
Mihir Gupta: Cantor Research Institute, Blauvelt, NY 10913, USA

Risks, 2025, vol. 13, issue 9, 1-14

Abstract: The EU Artificial Intelligence Act (Regulation (EU) 2024/1689) designates AI systems used in life and health insurance underwriting as high-risk systems, imposing rigorous requirements for bias testing, technical documentation, and post-deployment monitoring. Leveraging 12.4 million quote–bind–claim observations from four pan-European insurers (2019 Q1–2024 Q4), we evaluate how compliance affects premium schedules, loss ratios, and solvency positions. We estimate gradient-boosted decision tree (Extreme Gradient Boosting (XGBoost)) models alongside benchmark GLMs for mortality, morbidity, and lapse risk, using Shapley Additive Explanations (SHAP) values for explainability. Protected attributes (gender, ethnicity proxy, disability, and postcode deprivation) are excluded from training but retained for audit. We measure bias via statistical parity difference, disparate impact ratio, and equalized odds gap against the 10 percent tolerance in regulatory guidance, and then apply counterfactual mitigation strategies—re-weighing, reject option classification, and adversarial debiasing. We simulate impacts on expected loss ratios, the Solvency II Standard Formula Solvency Capital Requirement (SCR), and internal model economic capital. To translate fairness breaches into compliance risk, we compute expected penalties under the Act’s two-tier fine structure and supervisory detection probabilities inferred from GDPR enforcement. Under stress scenarios—full retraining, feature excision, and proxy disclosure—preliminary results show that bottom-income quintile premiums exceed fair benchmarks by 5.8 percent (life) and 7.2 percent (health). Mitigation closes 65–82 percent of these gaps but raises capital requirements by up to 4.1 percent of own funds; expected fines exceed rectification costs once detection probability surpasses 9 percent. We conclude that proactive adversarial debiasing offers insurers a capital-efficient compliance pathway and outline implications for enterprise risk management and future monitoring.

Keywords: algorithmic bias; EU AI Act; life insurance underwriting; fairness; Solvency II (search for similar items in EconPapers)
JEL-codes: C G0 G1 G2 G3 K2 M2 M4 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-9091/13/9/160/pdf (application/pdf)
https://www.mdpi.com/2227-9091/13/9/160/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jrisks:v:13:y:2025:i:9:p:160-:d:1729920

Access Statistics for this article

Risks is currently edited by Mr. Claude Zhang

More articles in Risks from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().