Abstract
Variable annuities are important financial products that result in 100 billion sales in 2018. These products contain complex guarantees that are computationally expensive to value, and insurance companies are turning to machine learning for the valuation of large portfolios of variable annuity policies. Although earlier studies, exemplified by the regression modelling approach, have shown promising results, the valuation accuracy is unsatisfying. In this paper, we show that one main cause for the poor valuation accuracy is the inefficient selection of representative policies. To overcome this problem, we propose a novel transfer-learning based portfolio valuation framework. The framework first builds a backbone deep neural network using historical Monte Carlo simulation results. The backbone network provides a valuation-driven representation for selecting the policies that best represent a large portfolio. Furthermore, the transferred network provides a way to adaptively extrapolate from these representative policies to the remaining policies in the portfolio. By overcoming a major difficulty faced by the popular Kriging model, the need of matrix inversion, the transferred network can handle a large number of representative policies to sufficiently cover a diverse portfolio.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cheng, X., Luo, W., Gan, G., Li, G.: Deep neighbor embedding for evaluation of large portfolios of variable annuities. In: Douligeris, C., Karagiannis, D., Apostolou, D. (eds.) KSEM 2019. LNCS (LNAI), vol. 11775, pp. xx–xx. Springer, Cham (2019)
Gan, G.: Application of data clustering and machine learning in variable annuity valuation. Insur. Math. Econ. 53(3), 795–801 (2013). https://doi.org/10.1016/j.insmatheco.2013.09.021
Gan, G.: Application of metamodeling to the valuation of large variable annuity portfolios. In: Proceedings of the Winter Simulation Conference, pp. 1103–1114 (2015)
Gan, G.: Valuation of large variable annuity portfolios using linear models with interactions. Risks 6(3), 71 (2018). https://doi.org/10.3390/risks6030071
Gan, G., Huang, J.: A data mining framework for valuing large portfolios of variable annuities. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1467–1475 (2017). https://doi.org/10.1145/3097983.3098013
Gan, G., Lin, X.S.: Valuation of large variable annuity portfolios under nested simulation: a functional data approach. Insur. Math. Econ. 62, 138–150 (2015)
Gan, G., Valdez, E.A.: An empirical comparison of some experimental designs for the valuation of large variable annuity portfolios. Depend. Model. 4(1), 382–400 (2016). http://ssrn.com/abstract=2830879
Gan, G., Valdez, E.A.: Modeling partial greeks of variable annuities with dependence. Insur. Math. Econ. 76, 118–134 (2017). http://ssrn.com/abstract=2844509
Gan, G., Valdez, E.A.: Nested stochastic valuation of large variable annuity portfolios: Monte Carlo simulation and synthetic datasets. Data 3(3), 31 (2018). https://doi.org/10.3390/data303003110.3390/data3030031
Gan, G., Valdez, E.A.: Regression modeling for the valuation of large variable annuity portfolios. North Am. Actuarial J. 22(1), 40–54 (2018). http://ssrn.com/abstract=2808088
Hardy, M.: Investment Guarantees: Modeling and Risk Management for Equity-linked Life Insurance, vol. 215. Wiley, Hoboken (2003)
Hejazi, S.A., Jackson, K.R.: A neural network approach to efficient valuation of large portfolios of variable annuities. Insur. Math. Econ. 70, 169–181 (2016)
Hejazi, S.A., Jackson, K.R., Gan, G.: A spatial interpolation framework for efficient valuation of large portfolios of variable annuities. Quant. Finan. Econ. 1(2), 125–144 (2017). https://doi.org/10.3934/QFE.2017.2.125
IAA: Stochastic Modeling: Theory and Reality from an Actuarial Perspective. International Actuarial Association, Ontario, Canada (2010). http://share.actuaries.org/Documentation/StochMod_2nd_Ed_print_quality.pdf
Isaaks, E., Srivastava, R.: An Introduction to Applied Geostatistics. Oxford University Press, Oxford (1990)
Kleijnen, J.P.C.: A comment on blanning’s “metamodel for sensitivity analysis: the regression metamodel in simulation”. Interfaces 5(3), 21–23 (1975)
Tishby, N., Pereira, F.C., Bialek, W.: The information bottleneck method. Univ. Illinois 411(29–30), 368–377 (2000)
Tishby, N., Zaslavsky, N.: Deep learning and the information bottleneck principle. In: 2015 IEEE Information Theory Workshop (ITW), pp. 1–5. IEEE (2015)
Vu, H., Nguyen, T.D., Le, T., Luo, W., Phung, D.: Robust anomaly detection in videos using multilevel representations. In: Proceedings of Thirty-third AAAI Conference on Artificial Intelligence (AAAI), Honolulu, USA (2019)
Xu, W., Chen, Y., Coleman, C., Coleman, T.F.: Moment matching machine learning methods for risk management of large variable annuity portfolios. J. Econ. Dyn. Control 87, 1–20 (2018)
Acknowledgement
This work was supported by the International Cooperation Project of Institute of Information Engineering, Chinese Academy of Sciences under Grant No. Y7Z0511101, and Guangxi Key Laboratory of Trusted Software (No KX201528).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Cheng, X., Luo, W., Gan, G., Li, G. (2019). Fast Valuation of Large Portfolios of Variable Annuities via Transfer Learning. In: Nayak, A., Sharma, A. (eds) PRICAI 2019: Trends in Artificial Intelligence. PRICAI 2019. Lecture Notes in Computer Science(), vol 11672. Springer, Cham. https://doi.org/10.1007/978-3-030-29894-4_57
Download citation
DOI: https://doi.org/10.1007/978-3-030-29894-4_57
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-29893-7
Online ISBN: 978-3-030-29894-4
eBook Packages: Computer ScienceComputer Science (R0)