English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We present novel cross-sectional and longitudinal claim count models forvehicle insurance built upon the Combined Actuarial Neural Network (CANN)framework proposed by Mario W\"uthrich and Michael Merz. The CANN approachcombines a classical actuarial model, such as a generalized linear model, witha neural network. This blending of models results in a two-component modelcomprising a classical regression model and a neural network part. The CANNmodel leverages the strengths of both components, providing a solid foundationand interpretability from the classical model while harnessing the flexibilityand capacity to capture intricate relationships and interactions offered by theneural network. In our proposed models, we use well-known log-linear claimcount regression models for the classical regression part and a multilayerperceptron (MLP) for the neural network part. The MLP part is used to processtelematics car driving data given as a vector characterizing the drivingbehavior of each insured driver. In addition to the Poisson and negativebinomial distributions for cross-sectional data, we propose a procedure fortraining our CANN model with a multivariate negative binomial (MVNB)specification. By doing so, we introduce a longitudinal model that accounts forthe dependence between contracts from the same insured. Our results reveal thatthe CANN models exhibit superior performance compared to log-linear models thatrely on manually engineered telematics features.

Telematics Combined Actuarial Neural Networks for Cross-Sectional and Longitudinal Claim Count Data