Incorporating heterogeneity into the prediction of total claim amount

Creative Commons License

Acar A., KARABEY U., Gregori D.

HACETTEPE JOURNAL OF MATHEMATICS AND STATISTICS, vol.47, no.5, pp.1321-1334, 2018 (SCI-Expanded) identifier identifier


The paper proposes an alternative predictor for the total claim amount of individuals that can be used for any type of non-life insurance products in which individuals may have multiple claims within one policy period. The impact of heterogeneity on expected total claim amount is investigated focusing on marginal predictions. Generalized linear mixed model (GLMM) is used for the amounts of loss per claim. Closed-form expression of the predictor is derived using marginal mean under GLMM and claim count distribution. Empirical studies are performed using a private health insurance data set of a Turkish insurance company. Proposed predictive model provides the lowest prediction errors among competing models according to the mean absolute error criterion.