Phase-type mixture-of-experts regression for loss severities

DOI10.1080/03461238.2022.2097019zbMATH Open1520.91310arXiv2111.00581OpenAlexW3209988119MaRDI QIDQ6156007FDOQ6156007

Authors: Martin Bladt, Jorge Yslas 

Publication date: 9 June 2023

Published in: Scandinavian Actuarial Journal (Search for Journal in Brave)

Abstract: The task of modeling claim severities is addressed when data is not consistent with the classical regression assumptions. This framework is common in several lines of business within insurance and reinsurance, where catastrophic losses or heterogeneous sub-populations result in data difficult to model. Their correct analysis is required for pricing insurance products, and some of the most prevalent recent specifications in this direction are mixture-of-experts models. This paper proposes a regression model that generalizes the latter approach to the phase-type distribution setting. More specifically, the concept of mixing is extended to the case where an entire Markov jump process is unobserved and where states can communicate with each other. The covariates then act on the initial probabilities of such underlying chain, which play the role of expert weights. The basic properties of such a model are computed in terms of matrix functionals, and denseness properties are derived, demonstrating their flexibility. An effective estimation procedure is proposed, based on the EM algorithm and multinomial logistic regression, and subsequently illustrated using simulated and real-world datasets. The increased flexibility of the proposed models does not come at a high computational cost, and the motivation and interpretation are equally transparent to simpler MoE models.

Full work available at URL: https://arxiv.org/abs/2111.00581

Recommendations

• Phase-type distributions for claim severity regression modeling
• A class of mixture of experts models for general insurance: theoretical developments
• Mixture Composite Regression Models with Multi-type Feature Selection
• A class of mixture of experts models for general insurance: application to correlated claim frequencies
• A New Class of Severity Regression Models with an Application to IBNR Prediction

zbMATH Keywords

multinomial regressionphase-type distributionsregression modelingmixture-of-experts

Mathematics Subject Classification ID

Actuarial mathematics (91G05) Applications of statistics to actuarial sciences and financial mathematics (62P05)

Cites Work

• Mortality modeling and regression with matrix distributions
• Penalised likelihood methods for phase-type dimension selection
• Matrix-Exponential Distributions in Applied Probability
• Title not available (Why is that?)
• Title not available (Why is that?)
• Inhomogeneous phase-type distributions and heavy tails
• Fitting inhomogeneous phase‐type distributions to data: the univariate and the multivariate case
• Partial likelihood
• Theory of partial likelihood
• Applied Probability and Queues
• Modelling censored losses using splicing: a global fit strategy with mixed Erlang and extreme value distributions
• Modeling loss data using mixtures of distributions
• A simple general approach to inference about the tail of a distribution
• Optimal bonus-malus systems using finite mixture models
• A class of mixture of experts models for general insurance: theoretical developments
• Extending composite loss models using a general framework of advanced computational tools
• A New Class of Severity Regression Models with an Application to IBNR Prediction

Cited In (6)

• A class of mixture of experts models for general insurance: theoretical developments
• Aggregate Markov models in life insurance: estimation via the EM algorithm
• Phase-type distributions for claim severity regression modeling
• Robust claim frequency modeling through phase-type mixture-of-experts regression
• Mixture Composite Regression Models with Multi-type Feature Selection
• Soft splicing model: bridging the gap between composite model and finite mixture model

This page was built for publication: Phase-type mixture-of-experts regression for loss severities

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6156007)