Fig 1.
Comparison of predictive distributions and observed distribution of the number of claims across six models for the French insurance dataset.
Each panel displays the model’s predictive distribution (blue bars) and the observed distribution of claim numbers (red bars) for a test subgroup with car age = 2 and driver age = 62 in the French motor claims frequency dataset. The title within each panel identifies the specific model used.
Table 1.
Model comparison based on mean squared error (MSE) of predicted distributions and corresponding standard errors (SE) for the French motor claims frequency dataset.
Fig 2.
Heat maps of the dissimilarity matrices showing clustering structure for the French motor claims frequency dataset.
Fig 3.
Comparison of predictive and observed claim number distributions across six models for the Belgian insurance dataset.
Each panel displays the model’s predictive distribution (blue bars) and the observed distribution of claim numbers (red bars) for a test subgroup with car age = 6 and driver age = 39 in the Belgian motor claims frequency dataset. The title within each panel identifies the specific model used.
Table 2.
Model comparison based on mean squared error (MSE) of predicted distributions and corresponding standard errors (SE) for the Belgian motor claims frequency dataset.
Fig 4.
Heat maps of the dissimilarity matrices showing clustering structure for the Belgian motor claims frequency dataset.
Fig 5.
Comparison of predictive and observed distributions of log(claim amounts) across six models for the French insurance dataset.
Each panel displays the model’s predictive density (red line) and the observed distribution of log(claim amounts) (blue histogram) for a test subgroup with car age = 9 and driver age = 38 in the French motor claims severity dataset. Each panel title indicates the corresponding model.
Table 3.
Model comparison based on mean squared error (MSE) of predicted distributions and corresponding standard errors (SE) for the French motor claims severity dataset.
Fig 6.
Heat maps of the dissimilarity matrices showing clustering structure for the French motor claims severity dataset.
Fig 7.
Scatter plots of log(claim amounts) versus car age for the French motor claims severity dataset.
Fig 8.
Scatter plots of log(claim amounts) versus driver age for the French motor claims severity dataset.
Fig 9.
Comparison of predictive and observed distributions of log(claim amounts) across six models for the Belgian insurance dataset.
Each panel displays the model’s predictive density (red line) and the observed distribution of log(claim amounts) (blue histogram) for a test subgroup with car age = 6 and driver age = 39 in the Belgian motor claims severity dataset. Each panel title indicates the corresponding model.
Table 4.
Model comparison based on mean squared error (MSE) of predicted distributions and corresponding standard errors (SE) for the Belgian motor claims severity dataset.
Fig 10.
Heat maps of the dissimilarity matrices showing clustering structure for the Belgian motor claims severity dataset.