In-processing of actuarial and equity fairness constraints for Neural networks

Donatien Hainaut ()
Additional contact information
Donatien Hainaut: Université catholique de Louvain, LIDAM/ISBA, Belgium

No 2025011, LIDAM Discussion Papers ISBA from Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA)

Abstract: This article introduces a novel in-processing method for integrating actuarial and equity fairness into neural networks used for actuarial valuation. We consider one primary network penalized during training to ensure balanced predictions (actuarial fairness) and independence from sensitive features (equity fairness). Global and local actuarial equilibrium is obtained by aligning the inter-quantile averages of predicted and observed responses. Meanwhile, a second auxiliary network penalizes the primary network for discriminatory predictions. The combined training algorithm eectively preserves predictive accuracy while mitigating discrimination. Numerical illustrations on real-world datasets demonstrate the method's ecacy in achieving fair and reliable insurance pricing models.

Keywords: Neural network; equity fairness; actuarial fairness; non-life pricing (search for similar items in EconPapers)
Pages: 24
Date: 2025-05-12
References: Add references at CitEc
Citations:

Downloads: (external link)
https://dial.uclouvain.be/pr/boreal/fr/object/bore ... tastream/PDF_01/view (application/pdf)

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:aiz:louvad:2025011

Access Statistics for this paper

More papers in LIDAM Discussion Papers ISBA from Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA) Voie du Roman Pays 20, 1348 Louvain-la-Neuve (Belgium). Contact information at EDIRC.
Bibliographic data for series maintained by Nadja Peiffer ().