Stratégie optimale de réduction de l'intervalle de confiance pour l'estimateur de la prime ajustée. Application en assurance automobile

Kmar Fersi (1) , Kamel Boukhetala (2) , Samir Ben Ammou (1)

1 Computational Mathematics Laboratory [Monastir]
2 Faculté des Mathématiques

The estimator of the adjusted premium developed by Necir and Boukhetala (2004) is considered. The problem of reducing the variance of this estimator is formulated as an optimization program with nonlinear stochastic constraints. An hybrid genetic algorithm is used for finding global optimal solutions, statistically explicable. An application to automobile insurance is developed.

Domaines: Gestion des risques [q-fin.RM]

Kmar Fersi, Kamel Boukhetala, Samir Ben Ammou. Stratégie optimale de réduction de l'intervalle de confiance pour l'estimateur de la prime ajustée. Application en assurance automobile. 2011. ⟨hal-00625684v2⟩