Individual Loss Reserving Using Paid-Incurred Data

Abstract

In this paper, the individual claim reserving model proposed by Pigeon et al. (2013) is extended to include paid and incurred data. Analytic expressions are derived for the expected ultimate losses, given observed development patterns. The usefulness of this new model is illustrated using a portfolio of general liability insurance policies. Detailed comparisons with existing approaches reveal that the paid-incurred individual reserving method proposed in this paper performs well and produces more accurate predictions.

Keywords: Stochastic Loss Reserving; General Insurance; Multivariate Skew Normal Distribution; Prediction