GAMLSS for Longitudinal Multivariate Claim Count Models

DOI10.1080/10920277.2023.2202707MaRDI QIDQ6583009zbMATH OpenFDO

Authors Jean-Philippe Boucher

Publication date 5 August 2024

Published in North American Actuarial Journal (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/10920277.2023.2202707

Mathematics Subject Classification ID

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

Review text

The paper's authors consider the various versions of the generalized additive models for location, scale, and shape (GAMLSS). Such models are mainly known for modeling the dependence between the number of claims and the contracts of the same insured over time. The authors demonstrate the advantages of the GAMLSS compared to other forecasting models. To illustrate the usefulness of the proposed model, the authors do so both theoretically and practically by applying particular cases of GAMLSS to real insurance data.

Recommendations

• Generalized Additive Models for Location, Scale and Shape
• Longitudinal modeling of insurance claim counts using jitters
• Multivariate insurance models: an overview
• Multilevel modeling of insurance claims using copulas
• Nonlife ratemaking and risk management with Bayesian generalized additive models for location, scale, and shape

Cites work

• A data driven binning strategy for the construction of insurance tariff classes
• A POSTERIORI RATEMAKING WITH PANEL DATA
• A practical guide to splines
• Actuarial Modelling of Claim Counts
• Bonus-Malus Systems
• Can automobile insurance telematics predict the risk of near-miss events?
• Constraints on concordance measures in bivariate discrete data
• Copula credibility for aggregate loss models
• Copula Regression for Compound Distributions with Endogenous Covariates with Applications in Insurance Deductible Pricing
• Flexible smoothing with B-splines and penalties. With comments and a rejoinder by the authors
• Gaussian Markov random field spatial models in GAMLSS
• Generalized additive models
• Generalized Additive Models for Location, Scale and Shape
• Hierarchical insurance claims modeling
• scientific article; zbMATH DE number 6734253 (Why is no real title available?)
• Longitudinal modeling of insurance claim counts using jitters
• Mean and dispersion modelling for policy claims costs
• Multivariate modelling of household claim frequencies in motor third-party liability insurance
• Non-life rate-making with Bayesian GAMs
• Nonlife ratemaking and risk management with Bayesian generalized additive models for location, scale, and shape
• PREDICTIVE CLAIM SCORES FOR DYNAMIC MULTI-PRODUCT RISK CLASSIFICATION IN INSURANCE
• Predictive model assessment for count data
• Statistical foundations of actuarial learning and its applications
• Testing for random effects in compound risk models via Bregman divergence
• The design of an optimal bonus-malus system based on the Sichel distribution
• Unravelling the predictive power of telematics data in car insurance pricing

Cited in

(3)

• From point to probabilistic gradient boosting for claim frequency and severity prediction
• Automated machine learning in insurance
• A novel credibility-based estimation approach for multivariate Esscher premiums

This page was built for publication: GAMLSS for Longitudinal Multivariate Claim Count Models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6583009)