Tweedie’s compound Poisson model is a popular method to model data with probability mass at zero and nonnegative, highly right-skewed distribution. Motivated by wide applications of the Tweedie model
A collection of insurance datasets from real insurers or mutual companies, mostly from Europe and North America. Datasets can be used to model and understand risks in both life and non-life insurance.
As part of the seed LDRD in 2017 we generated catastrophe models to look at the value of resiliency from an insurance perspective. These data sets reflect the inputs and outputs of that analysis.