Collective reserving using individual claims data

The aim of this paper is to operationalize claims reserving based on general insurance individual claims data. We design a modeling architecture that is based on six different neural networks. Each network is a separate module that serves a certain modeling purpose. We apply our architecture to individual claims data and predict their settlement processes on a monthly time grid. A proof of concept is provided by benchmarking the resulting claims reserves with the ones received from the classical chain-ladder method which uses much coarser (aggregated) data.

[1]  María Dolores Martínez Miranda,et al.  Double Chain Ladder , 2012, ASTIN Bulletin.

[2]  G. McGuire,et al.  Individual Claim Loss Reserving Conditioned by Case Estimates , 2008, Annals of Actuarial Science.

[3]  Ragnar Norberg,et al.  Prediction of Outstanding Liabilities in Non-Life Insurance , 1993, ASTIN Bulletin.

[4]  Kevin Kuo,et al.  Individual Claims Forecasting with Bayesian Mixture Density Networks , 2020, ArXiv.

[5]  G. Samorodnitsky,et al.  Prediction of outstanding payments in a Poisson cluster model , 2011 .

[6]  R. Verrall,et al.  On distribution-free reserving and partial information , 2019 .

[7]  M. Braga,et al.  Exploratory Data Analysis , 2018, Encyclopedia of Social Network Analysis and Mining. 2nd Ed..

[8]  D. Ticconi.  Individual Claims Reserving in Creditor Protection Insurance Using Machine Learning , 2019, SSRN Electronic Journal.

[9]  Mario V. Wüthrich.  Machine learning in individual claims reserving , 2016 .

[10]  Andrea Gabrielli,et al.  A NEURAL NETWORK BOOSTED DOUBLE OVERDISPERSED POISSON CLAIMS RESERVING MODEL , 2019, ASTIN Bulletin.

[11]  E. Arjas,et al.  The Claims Reserving Problem in Non-Life Insurance: Some Structural Ideas , 1989, ASTIN Bulletin.

[12]  Stephan M. Bischofberger,et al.  Continuous chain-ladder with paid data , 2019, Scandinavian Actuarial Journal.

[13]  Łukasz Delong,et al.  Neural Networks for the Joint Development of Individual Payments and Claim Incurred , 2020, Risks.

[14]  Xian Zhou,et al.  Semiparametric model for prediction of individual claim loss reserving , 2009 .

[15]  Franco Moriconi,et al.  Claim Watching and Individual Claims Reserving Using Classification and Regression Trees , 2019 .

[16]  Jens Perch Nielsen,et al.  Statistical modelling and forecasting of outstanding liabilities in non-life insurance , 2012 .

[17]  Stig. I. Rosenlund.  Bootstrapping Individual Claim Histories , 2012, ASTIN Bulletin.

[18]  M. Denuit,et al.  INDIVIDUAL LOSS RESERVING WITH THE MULTIVARIATE SKEW NORMAL FRAMEWORK , 2013, ASTIN Bulletin: The Journal of the International Actuarial Association.

[19]  B. Jørgensen.  Exponential Dispersion Models , 1987 .

[20]  Christian Y. Robert,et al.  A machine learning approach for individual claims reserving in insurance , 2019, Applied Stochastic Models in Business and Industry.

[21]  Pierre-Emmanuel Thérond,et al.  A TREE-BASED ALGORITHM ADAPTED TO MICROLEVEL RESERVING AND LONG DEVELOPMENT CLAIMS , 2019, ASTIN Bulletin.

[22]  Claims Reserving Using Tweedie's Compound Poisson Model , 2003, ASTIN Bulletin.

[23]  R. Norberg.  Prediction of Outstanding Liabilities II. Model Variations and Extensions , 1999, ASTIN Bulletin.

[24]  Katrien Antonio,et al.  Micro-level stochastic loss reserving for general insurance , 2012 .

[25]  P. England,et al.  Analytic and bootstrap estimates of prediction errors in claims reserving , 1999 .

[26]  Ostap Okhrin,et al.  Infinitely Stochastic Micro Forecasting , 2019, 1908.10636.

[27]  C. R. Larsen.  An Individual Claims Reserving Model , 2007, ASTIN Bulletin.

[28]  Bent Jørgensen,et al.  Fitting Tweedie's Compound Poisson Model to Insurance Claims Data: Dispersion Modelling , 2002, ASTIN Bulletin.

[29]  The collective reserving model , 2019, Insurance: Mathematics and Economics.

[30]  Mario V. Wüthrich,et al.  From Generalized Linear Models to Neural Networks, and Back , 2019 .

[31]  Andrei L. Badescu,et al.  A MARKED COX MODEL FOR THE NUMBER OF IBNR CLAIMS: ESTIMATION AND APPLICATION , 2016, ASTIN Bulletin.

[32]  Leo Breiman,et al.  Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author) , 2001, Statistical Science.

[33]  Mathieu Pigeon,et al.  Individual Loss Reserving Using a Gradient Boosting-Based Approach , 2019, Risks.