B0191
Title: Autocalibration by balance correction in nonlife insurance pricing
Authors: Julien Trufin - Université Libre de Bruxelles (Belgium) [presenting]
Michel Denuit - Universite catholique de Louvain (Belgium)
Abstract: By exploiting massive amounts of data, machine learning techniques provide actuaries with predictors exhibiting high correlation with claim frequencies and severities. However, these predictors generally fail to achieve financial equilibrium and thus do not qualify as pure premiums. Autocalibration effectively addresses this issue since it ensures that every group of policyholders paying the same premium is on average self-financing. The effect of balance correction is further studied on resulting pure premiums. It is shown that this method is also beneficial in terms of out-of-sample, or predictive Tweedie deviance, Bregman divergence as well as concentration curves. Conditions are derived ensuring that the initial predictor and its balance-corrected version are ordered in Lorenz order. Finally, criteria are proposed to rank the balance-corrected versions of two competing predictors in the convex order.
