Machine Learning

Sparse Regression with Multi-type Regularized Feature Modeling

We develop the SMuRF algorithm that accurately and effectively solves the general problem of convex optimization with a differentiable loss function and multi-type penalty terms. We show in full detail how this algorithm creates sparse models, using varying combinations of Lasso-type penalties, and investigating and documenting all possible model choices.

Boosting insights in insurance tariff plans with tree-based machine learning methods

We adapt tree-based machine learning methods to the problem of insurance pricing, thereby leaving the comfort zone of both traditional ratemaking and machine learning. State-ofthe-art GLMs are compared to regression trees, random forests and gradient boosting machines.

A data driven binning strategy for the construction of insurance tariff classes

A fully data driven strategy to incorporate continuous risk factors and geographical information in an insurance tariff.

Data analytics for insurance loss modelling, telematics pricing and claims reserving.

PhD Thesis