Searcharxiv⌕ Search

arXiv subjects

Paul Wilsens

Publications and source records attributed to Paul Wilsens.

3 recordsLinked to original sources

Modelling the occurrence and reporting dynamics of weather-related home insurance claims

We study the occurrence and reporting dynamics of weather-related claims in private home insurance, combining detailed portfolio and claim information with publicly available high-resolution weather data. Existing approaches typically start from an identified severe weather event, such as a hailstorm, and model the dynamics of the claims caused by that event. In practice, however, claims arise under moderate as well as severe conditions, and the claims handling process runs continuously. An insurer therefore requires insight into the occurrence and reporting of claims on every calendar day. Modelling all calendar days jointly poses two challenges: recently occurred claims are only partially reported, and days with severe weather are rare while accounting for a large share of the claims. We propose a multi-regime EM-XGBoost framework that addresses both: an expectation-maximisation setup accounts for the incurred-but-not-reported (IBNR) claims, while a data-driven regime structure lets the occurrence and reporting dynamics differ across weather conditions. In a case study on a Dutch home insurance portfolio, we compare single- and two-regime specifications for two spatial resolutions: the country as a whole, and its individual regions. We find that the regional two-regime model outperforms the regional single-regime model as well as both national models, indicating that the benefit of a multi-regime setting depends on a sufficiently granular spatial resolution. We also show that daily covariates constructed from hourly weather observations, capturing the duration and the intra-day timing of severe weather, improve both the occurrence and the reporting model.

stat.AP↗

Machine learning in an expectation-maximisation framework for nowcasting

Decision making often occurs in the presence of incomplete information, leading to the under- or overestimation of risk. Leveraging the observable information to learn the complete information is called nowcasting. In practice, incomplete information is often a consequence of reporting or observation delays. In this paper, we propose an expectation-maximisation (EM) framework for nowcasting that uses machine learning techniques to model both the occurrence as well as the reporting process of events. We allow for the inclusion of covariate information specific to the occurrence and reporting periods as well as characteristics related to the entity for which events occurred. We demonstrate how the maximisation step and the information flow between EM iterations can be tailored to leverage the predictive power of neural networks and (extreme) gradient boosting machines (XGBoost). With simulation experiments, we show that we can effectively model both the occurrence and reporting of events when dealing with high-dimensional covariate information. In the presence of non-linear effects, we show that our methodology outperforms existing EM-based nowcasting frameworks that use generalised linear models in the maximisation step. Finally, we apply the framework to the reporting of Argentinian Covid-19 cases, where the XGBoost-based approach again is most performant.

stat.ML↗

Reducing the dimensionality and granularity in hierarchical categorical variables

Hierarchical categorical variables often exhibit many levels (high granularity) and many classes within each level (high dimensionality). This may cause overfitting and estimation issues when including such covariates in a predictive model. In current literature, a hierarchical covariate is often incorporated via nested random effects. However, this does not facilitate the assumption of classes having the same effect on the response variable. In this paper, we propose a methodology to obtain a reduced representation of a hierarchical categorical variable. We show how entity embedding can be applied in a hierarchical setting. Subsequently, we propose a top-down clustering algorithm which leverages the information encoded in the embeddings to reduce both the within-level dimensionality as well as the overall granularity of the hierarchical categorical variable. In simulation experiments, we show that our methodology can effectively approximate the true underlying structure of a hierarchical covariate in terms of the effect on a response variable, and find that incorporating the reduced hierarchy improves the balance between model fit and complexity. We apply our methodology on a real dataset and find that the reduced hierarchy is an improvement over the original hierarchical structure and reduced structures proposed in the literature.

stat.ME↗