A NEURAL NETWORK BOOSTED DOUBLE OVERDISPERSED POISSON CLAIMS RESERVING MODEL

DOI10.1017/asb.2019.33zbMath1431.91328OpenAlexW2996283134WikidataQ126555831 ScholiaQ126555831MaRDI QIDQ5213437

Andrea Gabrielli

Publication date: 3 February 2020

Published in: ASTIN Bulletin (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1017/asb.2019.33

zbMATH Keywords

neural networkembeddingboostingclaim countsclaim amountschain-ladder reservesclaims reserving in insurancelearning across portfolioscross-classified overdispersed Poisson model

Mathematics Subject Classification ID

Actuarial mathematics (91G05)

Related Items (7)

The balance property in neural network modelling ⋮ Stochastic loss reserving with mixture density neural networks ⋮ Collective reserving using individual claims data ⋮ Dispersion modelling of outstanding claims with double Poisson regression models ⋮ Robust claim frequency modeling through phase-type mixture-of-experts regression ⋮ SynthETIC: an individual insurance claim simulator with feature control ⋮ An individual claims reserving model for reported claims

Uses Software

• R
• DCL
• ISLR

Cites Work

• Multilayer feedforward networks are universal approximators
• Double Chain Ladder
• BAYESIAN CHAIN LADDER MODELS
• 10.1162/153244303322533223
• An Introduction to Statistical Learning
• Approximation by superpositions of a sigmoidal function
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: A NEURAL NETWORK BOOSTED DOUBLE OVERDISPERSED POISSON CLAIMS RESERVING MODEL