Hostname: page-component-cd9895bd7-dzt6s Total loading time: 0 Render date: 2024-12-26T21:03:13.172Z Has data issue: false hasContentIssue false
  • English
  • Français

AI in actuarial science – a review of recent advances – part 2

Published online by Cambridge University Press:  26 August 2020

Ronald Richman Open the ORCID record for Ronald Richman [Opens in a new window]
Ronald Richman*
Affiliation:
QED Actuaries and Consultants
*
Email: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

Rapid advances in artificial intelligence (AI) and machine learning are creating products and services with the potential not only to change the environment in which actuaries operate, but also to provide new opportunities within actuarial science. These advances are based on a modern approach to designing, fitting and applying neural networks, generally referred to as “Deep Learning”. This paper investigates how actuarial science may adapt and evolve in the coming years to incorporate these new techniques and methodologies. Part 1 of this paper provides background on machine learning and deep learning, as well as an heuristic for where actuaries might benefit from applying these techniques. Part 2 of the paper then surveys emerging applications of AI in actuarial science, with examples from mortality modelling, claims reserving, non-life pricing and telematics. For some of the examples, code has been provided on GitHub so that the interested reader can experiment with these techniques for themselves. Part 2 concludes with an outlook on the potential for actuaries to integrate deep learning into their activities. Finally, a supplementary appendix discusses further resources providing more in-depth background on machine learning and deep learning.

Keywords

Actuarial scienceDeep learningMachine learningInsuranceTelematics
Type
Review
Information
Annals of Actuarial Science , Volume 15 , Issue 2 , July 2021 , pp. 230 - 258
Copyright
© Institute and Faculty of Actuaries 2020

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D.G., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., Wicke, M., Yu, Y. … Zheng, X. (2016). TensorFlow: A System for Large-Scale Machine Learning. Paper presented at the OSDI.Google Scholar
Allaire, J. & Chollet, F. (2018). R interface to Keras: RStudio, Google. Available online at the address https://cloud.r-project.org/web/packages/keras/index.html [accessed 24-Jul-2018].Google Scholar
Bornhuetter, R.L. & Ferguson, R.E. (1972, November). The actuary and IBNR. In Proceedings of the Casualty Actuarial Society (Vol. 59, No. 112, pp. 181–195).Google Scholar
Boucher, J.-P., Côté, S. & Guillen, M. (2017). Exposure as duration and distance in telematics motor insurance using generalized additive models. Risks, 5(4), 54.CrossRefGoogle Scholar
Bühlmann, H., De Felice, M., Gisler, A., Moriconi, F. & Wüthrich, M. (2009). Recursive credibility formula for chain ladder factors and the claims development result. ASTIN Bulletin: The Journal of the IAA, 39(1), 275–306.CrossRefGoogle Scholar
Cairns, A.J.G., Blake, D. & Dowd, K. (2006). A two-factor model for stochastic mortality with parameter uncertainty: theory and calibration. Journal of Risk & Insurance, 73(4), 687–718. doi: 10.1111/j.1539-6975.2006.00195.x CrossRefGoogle Scholar
Charpentier, A. (2014). Computational Actuarial Science With R: CRC Press, Boca Raton.CrossRefGoogle Scholar
Chollet, F. (2015). Keras. Available online at the address keras.io [accessed 24-Jul-2018].Google Scholar
Chollet, F. (2017). Deep Learning With Python: Manning Publications Co, New York.Google Scholar
Chollet, F. & Allaire, J. (2018). Deep Learning With R: Manning Publications Co, New York.Google Scholar
Chung, J., Gulcehre, C., Cho, K. & Bengio, Y. (2015). Gated feedback recurrent neural networks. Paper presented at the International Conference on Machine Learning.Google Scholar
Currie, I.D. (2016). On fitting generalized linear and non-linear models of mortality. Scandinavian Actuarial Journal, 2016(4), 356–383.CrossRefGoogle Scholar
Dal Moro, E., Cuypers, F. & Miehe, P. (2016). Non-life Reserving Practices. Available online at the address https://www.actuaries.org/ASTIN/Documents/ASTIN_WP_NL_Reserving_Report1.0_2016-06-15.pdf [accessed 24-Jul-2018].Google Scholar
De Brébisson, A., Simon, É., Auvolat, A., Vincent, P. & Bengio, Y. (2015). Artificial neural networks applied to taxi destination prediction. Available online at the address arXiv:1508.00021 [accessed 24-Jul-2018].Google Scholar
Dong, W., Li, J., Yao, R., Li, C., Yuan, T. & Wang, L. (2016). Characterizing driving styles with deep learning. Available online at the address arXiv:1607.03611 [accessed 24-Jul-2018].Google Scholar
Dong, W., Yuan, T., Yang, K., Li, C. & Zhang, S. (2017). Autoencoder regularized network for driving style representation learning. Available online at the address arXiv:1701.01272 [accessed 24-Jul-2018].Google Scholar
Dowle, M. & Srinivasan, A. (2018). data.table. CRAN. Available online at the address https://cran.r-project.org/web/packages/data.table/index.html [accessed 24-Jul-2018].Google Scholar
Efron, B. & Hastie, T. (2016). Computer Age Statistical Inference (Vol. 5): Cambridge University Press, Cambridge.CrossRefGoogle Scholar
England, P. & Verrall, R. (1999). Analytic and bootstrap estimates of prediction errors in claims reserving. Insurance: Mathematics and Economics, 25(3), 281–293.Google Scholar
Ezzini, S., Berrada, I. & Ghogho, M. (2018). Who is behind the wheel? Driver identification and fingerprinting. Journal of Big Data, 5(1), 9.CrossRefGoogle Scholar
Friedman, J., Hastie, T. & Tibshirani, R. (2009). The Elements of Statistical Learning : Data Mining, Inference, and Prediction. Springer-Verlag, New York.Google Scholar
Gabrielli, A. & Wüthrich, M. (2018). An individual claims history simulation machine. Risks, 6(2), 29.CrossRefGoogle Scholar
Gal, Y. & Ghahramani, Z. (2016). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. Paper presented at the international conference on machine learning.Google Scholar
Gan, G. & Lin, X.S. (2015). Valuation of large variable annuity portfolios under nested simulation: a functional data approach. Insurance: Mathematics and Economics, 62, 138–150.Google Scholar
Gao, G., Meng, S. & Wüthrich, M. (2018). Claims Frequency Modeling Using Telematics Car Driving Data. Available online at the address https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3102371 [accessed 24-Jul-2018].Google Scholar
Gao, G. & Wüthrich, M. (2017). Feature Extraction from Telematics Car Driving Heatmaps. Available online at the address https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3070069 [accessed 24-Jul-2018].Google Scholar
Gelman, A. & Hill, J. (2007). Data Analysis Using Regression and Multilevelhierarchical Models (Vol. 1): Cambridge University Press, New York, NY, USA.Google Scholar
Gisler, A. & Wüthrich, M. (2008). Credibility for the chain ladder reserving method. ASTIN Bulletin: The Journal of the IAA, 38(2), 565–600.CrossRefGoogle Scholar
Golden, L., Brockett, P., Ai, J. & Kellison, B. (2016). Empirical evidence on the use of credit scoring for predicting insurance losses with psycho-social and biochemical explanations. North American Actuarial Journal, 20(3), 233–251. doi: 10.1080/10920277.2016.1209118 CrossRefGoogle Scholar
Goodfellow, I., Bengio, Y. & Courville, A. (2016). Deep Learning: MIT Press, Cambridge, MA.Google Scholar
Guo, C. & Berkhahn, F. (2016). Entity embeddings of categorical variables. Available online at the address arXiv:1604.06737 [accessed 24-Jul-2018].Google Scholar
Hainaut, D. (2018a). A neural-network analyzer for mortality forecast. Astin Bulletin, 48(2), 481–508. doi: 10.1017/asb.2017.45 CrossRefGoogle Scholar
Hainaut, D. (2018b). A self-organizing predictive map for non-life insurance. SSRN, 2018(29 June). Available online at the address https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3099979 [accessed 24-Jul-2018].CrossRefGoogle Scholar
Hazelton, M.L. (2014). Kernel Smoothing. In Balakrishnan, N., Colton, T., Everitt, B., Piegorsch, W., Ruggeri, F. & Teugels, J.L. (Eds.), Wiley StatsRef: Statistics Reference Online. doi: 10.1002/9781118445112.stat06538.CrossRefGoogle Scholar
Hejazi, S. & Jackson, K. (2016). A neural network approach to efficient valuation of large portfolios of variable annuities. Insurance: Mathematics and Economics, 70, 169–181.Google Scholar
Hejazi, S. & Jackson, K. (2017). Efficient valuation of SCR via a neural network approach. Journal of Computational and Applied Mathematics, 313, 427–439.CrossRefGoogle Scholar
Hyndman, R.J., Athanasopoulos, G., Razbash, S., Schmidt, D., Zhou, Z., Khan, Y., … Wang, E. (2015). Forecast: forecasting functions for time series and linear models. R package version, 6(6), 7.Google Scholar
James, G., Witten, D., Hastie, T. & Tibshirani, R. (2013). An Introduction To Statistical Learning (Vol. 112): Springer.CrossRefGoogle Scholar
Kassambara, A. (2018). ggpubr: ‘ggplot2’ Based Publication Ready Plots. Available online at the address https://cran.r-project.org/web/packages/ggpubr/index.html [accessed 24-Jul-2018].Google Scholar
Kingma, D.P. & Ba, J. (2014). Adam: A method for stochastic optimization. Available online at the address arXiv:1412.6980 [accessed 24-Jul-2018].Google Scholar
Kohonen, T. (1990). The self-organizing map. Proceedings of the IEEE, 78(9), 1464–1480.Google Scholar
Kuo, K. (2018a). DeepTriangle. GitHub. Available online at the address https://github.com/kevinykuo/deeptriangle [accessed 24-Jul-2018].Google Scholar
Kuo, K. (2018b). DeepTriangle: A Deep Learning Approach to Loss Reserving Available online at the address arXiv:1804.09253 [accessed 24-Jul-2018].Google Scholar
Lakshminarayanan, B., Pritzel, A. & Blundell, C. (2017). Simple and scalable predictive uncertainty estimation using deep ensembles. Paper presented at the Advances in Neural Information Processing Systems.Google Scholar
Lee, R.D. & Carter, L.R. (1992). Modeling and forecasting US mortality. Journal of the American Statistical Association, 87(419), 659–671.Google Scholar
LeNail, A. (2019). NN-SVG: Publication-Ready Neural Network Architecture Schematics. Journal of Open Source Software, 4(33), 747. doi: https://doi.org/10.21105/joss.00747.CrossRefGoogle Scholar
Maaten, L. & Hinton, G. (2008). Visualizing data using t-SNE. Journal of Machine Learning Research, 9, 2579–2605.Google Scholar
Mack, T. (1993). Distribution-free calculation of the standard error of chain ladder reserve estimates. Astin Bulletin, 23(02), 213–225.CrossRefGoogle Scholar
Makridakis, S., Spiliotis, E. & Assimakopoulos, V. (2018a). The M4 Competition: results, findings, conclusion and way forward. International Journal of Forecasting. https://doi.org/10.1016/j.ijforecast.2018.06.001 [accessed 24-Jul-2018].CrossRefGoogle Scholar
Makridakis, S., Spiliotis, E. & Assimakopoulos, V. (2018b). Statistical and machine learning forecasting methods: concerns and ways forward. PLOS ONE, 13(3), e0194889. doi: 10.1371/journal.pone.0194889 CrossRefGoogle ScholarPubMed
Meyers, G. (2015). Stochastic Loss Reserving Using Bayesian MCMC Models. Casualty Actuarial Society, New York.Google Scholar
Meyers, G. & Shi, P. (2011). Loss Reserving Data Pulled From NAIC Schedule P, 2011. Available online at the address https://www.casact.org/research/index.cfm?fa=loss_reserves_data [accessed 24-Jul-2018].Google Scholar
Noll, A., Salzmann, R. & Wüthrich, M. (2018). Case Study: French Motor Third-Party Liability Claims. Available online at the address https://ssrn.com/abstract=3164764 [accessed 24-Jul-2018].Google Scholar
Ohlsson, E. & Johansson, B. (2010). Non-Life Insurance Pricing With Generalized Linear Models (Vol. 2): Springer.CrossRefGoogle Scholar
Parodi, P. (2014). Pricing In General Insurance: CRC Press, Boca Raton.CrossRefGoogle Scholar
R Core Team. (2018). R: A Language And Environment For Statistical Computing. Vienna, Austria: R Foundation for Statistical Computing. Available online at the address https://www.R-project.org [accessed 24-Jul-2018].Google Scholar
Racine, J. & Hayfield, T. (2018). np: Nonparametric Kernel Smoothing Methods for Mixed Data Types: CRAN. Available online at the address https://cran.r-project.org/web/packages/np/index.html [accessed 24-Jul-2018].Google Scholar
Richman, R. (2020). AI in actuarial science – a review of recent advances – part 1. Annals of Actuarial Science.Google Scholar
Richman, R. & Wüthrich, M.V. (2018). A neural network extension of the Lee-Carter model to multiple populations. Available online at the address https://ssrn.com/abstract=3270877 [accessed 24-Jul-2018].Google Scholar
Riedmiller, M. & Braun, H. (1993). A direct adaptive method for faster backpropagation learning: The RPROP algorithm. Paper presented at the IEEE International Conference on Neural Networks, 1993.CrossRefGoogle Scholar
Schmidt, K. (2017). A Bibliography on Loss Reserving. Available online at the address https://www.math.tu-dresden.de/sto/schmidt/dsvm/reserve.pdf [accessed 24-Jul-2018].Google Scholar
Shmueli, G. (2010). To explain or to predict? Statistical Science, 289–310.Google Scholar
Smith, M., Beyers, F. & De Villiers, J. (2016). A method of parameterising a feed forward multi-layered perceptron artificial neural network, with reference to South African financial markets. South African Actuarial Journal, 16(1), 35–67.Google Scholar
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1), 1929–1958.Google Scholar
Turner, H. & Firth, D. (2007). Generalized nonlinear models in R: An overview of the gnm package.Google Scholar
Verbelen, R., Antonio, K. & Claeskens, G. (2018). Unravelling the predictive power of telematics data in car insurance pricing. Journal of the Royal Statistical Society: Series C (Applied Statistics) (Pre-print). doi: 10.1111/rssc.12283 Google Scholar
Villegas, A., Kaishev, V. & Millossovich, P. (2015). StMoMo: An R package for stochastic mortality modelling: CRAN. Available online at the address https://cran.r-project.org/web/packages/StMoMo/index.html [accessed 24-Jul-2018].Google Scholar
Weidner, W., Transchel, F. & Weidner, R. (2016a). Telematic driving profile classification in car insurance pricing. Annals of Actuarial Science, 11(2), 213–236. doi: 10.1017/S1748499516000130 CrossRefGoogle Scholar
Weidner, W., Transchel, F.W.G. & Weidner, R. (2016b). Classification of scale-sensitive telematic observables for risk individual pricing. European Actuarial Journal, 6(1), 3–24. doi: 10.1007/s13385-016-0127-x CrossRefGoogle Scholar
Wickham, H. (2016). Ggplot2: Elegant Graphics for Data Analysis: Springer, Berlin.CrossRefGoogle Scholar
Wijnands, J., Thompson, J., Aschwanden, G. & Stevenson, M. (2018). Identifying behavioural change among drivers using Long Short-Term Memory recurrent neural networks. Transportation Research Part F: Traffic Psychology and Behaviour, 53, 34–49.CrossRefGoogle Scholar
Wilmoth, J.R. & Shkolnikov, V. (2010). Human Mortality Database. University of California.Google Scholar
Wood, S. (2017). Generalized Additive Models: An Introduction With R. Chapman and Hall/CRC, Boca Raton.CrossRefGoogle Scholar
Wüthrich, M. (2018a). Neural networks applied to chain-ladder reserving. SSRN. Available online at the address https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2966126 [accessed 24-Jul-2018].CrossRefGoogle Scholar
Wüthrich, M. (2018b). v-a Heatmap Simulation Machine. Version 1. Available online at the address https://people.math.ethz.ch/~wueth/simulation.html [accessed 24-Jul-2018].Google Scholar
Wüthrich, M. & Buser, C. (2018). Data analytics for non-life insurance pricing. Available online at the address https://ssrn.com/abstract=2870308 [accessed 24-Jul-2018].Google Scholar
Wüthrich, M.V. (2017). Covariate selection from telematics car driving data. European Actuarial Journal, 7(1), 89–108.CrossRefGoogle Scholar
Wüthrich, M.V. & Merz, M. (2008). Stochastic Claims Reserving Methods In Insurance (Vol. 435): John Wiley & Sons, New Jersey.Google Scholar
Zarkadoulas, A. (2017). Neural Network Algorithms For The Development Of Individual Losses. University of Lausanne, Lausanne.Google Scholar
Supplementary material: File

Richman supplementary material

Richman supplementary material

Download Richman supplementary material(File)
File 26.5 KB