摘要：This article proposes using credibility theory in the context of stochastic claims reserving.We consider the situation where an insurer has access to the claims experience of its peer competitorsand has the potential to improve prediction of outstanding liabilities by incorporatinginformation from other insurers. Based on the framework of Bayesian linear models, we showthat the development factor in the classical chain-ladder setting has a credibility expression, i.e.a weighted average of the prior mean and the best estimate from the data. In the empiricalanalysis, we examine loss triangles for the line of commercial auto insurance from a portfolio ofinsurers in the US. We employ hierarchical model for the specification of prior and show thatprediction could be improved through borrowing strength among insurers based on a hold-outsample validation.
关键词：Bayesian Modeling; Chain-ladder method; Hierarchical model
