Autocalibration and Tweedie-dominance for insurance pricing with machine learning

DOI10.1016/j.insmatheco.2021.09.001zbMath1475.91295arXiv2103.03635OpenAlexW3200416260MaRDI QIDQ2665871

Julien Trufin, Arthur Charpentier, Michel M. Denuit

Publication date: 19 November 2021

Published in: Insurance Mathematics \& Economics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2103.03635

zbMATH Keywords

convex orderrisk classificationautocalibrationmethod of marginal totalsTweedie distribution family

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Actuarial mathematics (91G05)

Related Items (6)

Testing for more positive expectation dependence with application to model comparison ⋮ Local bias adjustment, duration-weighted probabilities, and automatic construction of tariff cells ⋮ Isotonic recalibration under a low signal-to-noise ratio ⋮ Deep quantile and deep composite triplet regression ⋮ Bayesian CART models for insurance claims frequency ⋮ Model selection with Gini indices under auto-calibration

Uses Software

• CASdatasets

Cites Work

• Making Tweedie's compound Poisson model more accessible
• Stochastic orders
• Expectation dependence of random variables, with an application in portfolio theory
• Global dependence stochastic orders
• Model selection based on Lorenz and concentration curves, Gini indices and convex order
• Bias regularization in neural network models for general insurance pricing
• Local Regression and Likelihood

This page was built for publication: Autocalibration and Tweedie-dominance for insurance pricing with machine learning