A Unified Approach to Sparse Tweedie Modeling of Multisource Insurance Claim Data

Abstract

Actuarial practitioners now have access to multiple sources of insurance data corresponding to various situations: multiple business lines, umbrella coverage, multiple hazards, and so on. Despite the wide use and simple nature of single-target approaches, modeling these types of data may benefit from an approach performing variable selection jointly across the sources. We propose a unified algorithm to perform sparse learning of such fused insurance data under the Tweedie (compound Poisson) model. By integrating ideas from multitask sparse learning and sparse Tweedie modeling, our algorithm produces flexible regularization that balances predictor sparsity and between-sources sparsity. When applied to simulated and real data, our approach clearly outperforms single-target modeling in both prediction and selection accuracy, notably when the sources do not have exactly the same set of predictors. An efficient implementation of the proposed algorithm is provided in our R package MStweedie, which is available at https://github.com/fontaine618/MStweedie. Supplementary materials for this article are available online.