Quelles limites pour l'application des algorithmes d'apprentissage en assurance ?

DetraNote 2020-2

Abstract

Une étape essentielle du processus de tarification est le choix de l’algorithme qui permettra de calculer la prime à partir de données passées. En assurance, les modèles prédictifs sont partout : il peut s’agir de calculer la prime demandée pour couvrir les dommages causés à un bien, ou encore d’un score interne de suspicion de fraude sur un sinistre. Ce papier discute des limites de l’application des algorithmes prédictifs en assurance en revenant sur les notions de segmentation des risques et d’hétérogénéité.

Sector: Insurance

Expertise: Pricing

Authors: Arthur Charpentier et

Michel Denuit

 

Publisher: Detralytics

Date: May 2020

Language: French

Pages: 33

Reference : Detra Note 2020-2

About the authors

Arthur Charpentier

PhD, Fellow of the French Institute of Actuaries, Full Professor at the Département de Mathématiques, Université du Québec à Montréal (UQAM), Canada, and at Université de Rennes, France. He previously served as Senior Editor for the Journal of Risk and Insurance; he is now Co‑Editor of the European Actuarial Journal and sits on the editorial board of the ASTIN Bulletin. Additionally, he served as Director of Studies for the Data Science for Actuaries program at the French Institute of Actuaries. He teaches courses in predictive modeling, insurance and actuarial science, mathematical economics, and statistical and econometric methods.
Michel Denuit

Michel Denuit

Michel is a Scientific Advisor at Detralytics, as well as a professor in actuarial science at the Université Catholique de Louvain. He has international experience as a visiting professor, and has promoted many projects in collaboration with the industry. At Detralytics, Michel coaches young talents, provides cutting-edge training, fosters innovation and oversees R&D projects.

LAST call

Don't miss our upcoming Lunch & Learn