Abstract
Generalized linear models have the important property of providing unbiased estimates on a portfolio level. This implies that generalized linear models manage to provide accurate prices on a portfolio level. On the other hand, neural networks may provide very accurate prices on an individual policy level, but state-of-the-art use of neural networks does not pay any attention to unbiasedness on the portfolio level. This is an implicit consequence of applying early stopping rules in gradient descent methods for model fitting. In the present paper we discuss this deficiency and we provide two different techniques to overcome this drawback of neural network model fitting.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bailey RA (1963) Insurance rates with minimum bias. Proc CAS 50:4–11
Barndorff-Nielsen O (2014) Information and exponential families: in statistical theory. Wiley, Hoboken
Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Wadsworth Statistics/Probability Series
Bühlmann H (1980) An economic premium principle. ASTIN Bull 11(1):52–60
Bühlmann H, Gisler A (2005) A course in credibility theory and its applications. Springer, Berlin
Denuit M, Maréchal X, Pitrebois S, Walhin J-F (2007) Actuarial modelling of claim counts. Wiley, Hoboken
Draxler F, Veschgini K, Salmhofer M, Hamprecht FA (2019) Essentially no barriers in neural network energy landscape. arXiv:1803.00885v5
Esscher F (1932) On the probability function in the collective theory of risk. Scand Actuar J 1932(3):175–195
Frees EW (2010) Regression modeling with actuarial and financial applications. Cambridge University Press, Cambridge
Garipov T, Izmailov P, Podoprikhin D, Vetrov D, Wilson AG (2018) Loss surfaces, mode connectivity, and fast ensembling of DNNs. arXiv:1802.10026v4
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press, Cambridge
Jørgensen B (1987) Exponential dispersion models. J R Stat Soc Ser B (Methodological) 49/2:127–145
Jung J (1968) On automobile insurance ratemaking. ASTIN Bull 5:41–48
McCullagh P, Nelder JA (1983) Generalized linear models. Chapman & Hall, London
Nelder JA, Wedderburn RWM (1972) Generalized linear models. J R Stat Soc Ser A (General) 135/3:370–384
Ohlsson E, Johansson B (2010) Non-life insurance pricing with generalized linear models. Springer, Berlin
Wüthrich MV, Buser C (2016) Data analytics for non-life insurance pricing. SSRN Manuscript ID 2870308, Version of June 4, 2019
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wüthrich, M.V. Bias regularization in neural network models for general insurance pricing. Eur. Actuar. J. 10, 179–202 (2020). https://doi.org/10.1007/s13385-019-00215-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13385-019-00215-z