Hello, I am learning about frequency and severity models.
I am trying to fit the data of an insurance company, the data are about fire, but the number of claims only was 800. And the total number of houses is 130000, I have model with a GLM poisson and binomial, but according deviance the models are not well.
Do you know some strategies or models when there are a small number of claims??

thanks in advance for your help..