Neural network embedding of the over-dispersed Poisson reserving model

DOI10.1080/03461238.2019.1633394zbMath1430.91076OpenAlexW2902471886WikidataQ127560299 ScholiaQ127560299MaRDI QIDQ5210997

Andrea Gabrielli, Ronald Richman, Mario V. Wüthrich

Publication date: 17 January 2020

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

Full work available at URL: https://doi.org/10.1080/03461238.2019.1633394

zbMATH Keywords

neural networknested modelsmean square error of predictionchain-ladder reservesclaims reserving in insurancecross-classified over-dispersed Poisson modellearning across portfoliosmodel blending

Mathematics Subject Classification ID

Applications of statistics to actuarial sciences and financial mathematics (62P05) Artificial neural networks and deep learning (68T07) Actuarial mathematics (91G05)

Related Items

A COLLECTIVE RESERVING MODEL WITH CLAIM OPENNESS, Stochastic loss reserving with mixture density neural networks, Dispersion modelling of outstanding claims with double Poisson regression models, Infinitely stochastic micro reserving, Modelling and understanding count processes through a Markov-modulated non-homogeneous Poisson process framework, An individual claims reserving model for reported claims, Life expectancy and lifespan disparity forecasting: a long short-term memory approach

Cites Work

• Multilayer feedforward networks are universal approximators
• Analytic and bootstrap estimates of prediction errors in claims reserving
• Credibility for the Chain Ladder Reserving Method
• BAYESIAN CHAIN LADDER MODELS
• 10.1162/153244303322533223
• Learning representations by back-propagating errors
• Approximation by superpositions of a sigmoidal function
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item