Medición de lapses en seguros de vida mediante modelos de predicción
Medición de lapses en seguros de vida mediante modelos de predicción
Contenido principal del artículo
Resumen
Las compañías de seguros están en constante medición de sus persistencias, por ello, identificar y analizar las tasas de cancelación denominadas lapses o tasas de caducidad, se ha convertido en una actividad de gran importancia debido a su rol determinante para tomar decisiones administrativas y financieras. Entender la dinámica de esta variable facilita la toma de decisiones, y permite identificar las variables que ocasionan cancelaciones de pólizas, es decir: el género, la edad, la ciudad, el tipo de producto, entre otros. Estas variables caracterizan el perfil del asegurado y condicionan una mayor o menor probabilidad de cancelar la póliza. Para analizar los perfiles de asegurados, se consideró utilizar modelos de regresión logística, redes neuronales y máquinas de soporte vectorial, con precisión de 73 %, 81,53 % y 60 %, respectivamente, mediante una base de datos de asegurados del mercado de Colombia con 134 102 registros, con 8 variables, lo que permitió predecir la probabilidad de cancelación y de renovación de una póliza de seguro de vida de acuerdo con las condiciones de las variables que perfilan a un asegurado.
Detalles del artículo
Referencias (VER)
Azzone, M., Barucci, E., Moncayo, G. G. & Marazzina, D. (2022). A machine learning model for lapse prediction in life insurance contracts. Expert Systems with Applications, 191, 116261. https://doi.org/10.1016/j.eswa.2021.116261
Bacinello, A. R. (2005). Endogenous model of surrender conditions in equity-linked life insurance. Insurance: Mathematics and Economics, 37(2), 270-296. https://doi.org/10.1016/j.insmatheco.2005.02.002
Bauer, D., Gao, J., Moenig, T., Ulm, E. R. & Zhu, N. (2017). Policyholder exercise behavior in life insurance: the state of affairs. North American Actuarial Journal, 21(4), 485-501. https://doi.org/10.1080/10920277.2017.1314816
Betancourt, G. A. (2005). Las máquinas de soporte vectorial (SVMs). Scientia et Technica, 11(27), 67-72. https://www.redalyc.org/pdf/849/84911698014.pdf
Canadian Institute of Actuarie. (2014). Lapse experience study for 10-year term insurance - report individual life experience subcommittee.
Cortés, C. & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20, 273-297. https://doi.org/10.1007/BF00994018
Cristianini, N. & Shawe-Taylor, J. (2000). An introduction to support vector machine and other kernel-based learning methods. Cambridge University Press https://doi.org/10.1017/CBO9780511801389
Eling, M. & Kochanski, M. (2013). Research on lapse in life insurance: what has been done and what needs to be done? Journal of Risk Finance, 14(4), 392-413. https://doi.org/10.1108/JRF-12-2012-0088
Eling, M. & Kiesenbauer, D. (2014). What policy features determine life insurance lapse? An analysis of the German market. Journal of Risk and Insurance, 81(2), 241-269. https://doi.org/10.1111/j.1539-6975.2012.01504.x
Fier, S. G. & Liebenberg, A. P. (2013). Life insurance lapse behavior. North American Actuarial Journal, 17(2), 153-167. https://doi.org/10.1080/10920277.2013.803438
Fiuza Pérez, M. y Rodríguez Pérez, J. C. (2000). La regresión logística: una herramienta versátil. Nefrología, 20(6), 477-565. https://www.revistanefrologia.com/es-la-regresion-logistica-una-herramienta-articulo-X0211699500035664
Goodacre, R., Neal, M. J. & Kell, D. B. (1996). Quantitative analysis of multivariate data using artificial neural networks: a tutorial review and applications to the deconvolution of pyrolysis mass spectra. Zentralblatt für Bakteriologie, 284(4), 516-539. https://doi.org/10.1016/S0934-8840(96)80004-1
Gottlieb, D. & Smetters, K. (2021). Lapse-based insurance. American Economic Review, 111(8), 2377-2416. https://doi.org/10.1257/aer.20160868
Guillén, M., Pérez, A. M. & Alcañiz, M, (2011). A logistic regression approach to estimating customer profit loss due to lapses in insurance. Document de Treball No. XREAP 2011-13. http://dx.doi.org/10.2139/ssrn.1942278
Harrell, F. E. (2015). Regression modeling strategies: with applications to linear models, logistic regression, and survival analysis (2nd ed.). Springer.
Hastie, T., Tibshirani, R. & Freidman, J. (2001). The elements of statistical learning: data mining, inference and prediction. Springer. http://dx.doi.org/10.1007/978-0-387-21606-5
He, K., Zhang, X., Ren, S. & Sun, J. (2015). Delving deep into rectifiers: surpassing human-level performance on imagenet classification. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, pp. 1026-1034. https://doi.org/10.1109/ICCV.2015.123
Heldt, R., Silveira, C. S. & Luce, F. B. (2021). Predicting customer value per product: from RFM to RFM/P. Journal of Business Research, 127, 444-453. https://doi.org/10.1016/j.jbusres.2019.05.001
Hosmer, D. W., Lemeshow, S. & Sturdivant, R. X. (2013). Applied logistic regression (3rd ed.). John Wiley & Sons. https://onlinelibrary.wiley.com/doi/chapter-epub/10.1002/9781118548387.fmatter
Hu, S., O’Hagan, A., Sweeney, J. & Ghahramani, M. (2021). A spatial machine learning model for analysing customers’ lapse behaviour in life insurance. Annals of Actuarial Science, 15(2), 367-393. https://doi.org/10.1017/S1748499520000329
Kiesenbauer, D. (2012). Main determinants of lapse in the German life insurance industry. North American Actuarial Journal, 16(1), 52-73. https://doi.org/10.1080/10920277.2012.10590632
Kim, C. (2005). Modeling surrender and lapse rates with economic variables. North American Actuarial Journal, 9(4), 56-70. https://doi.org/10.1080/10920277.2005.10596225
Kuo, W., Tsai, C. & Chen, W. K. (2003). An empirical study on the lapse rate: the cointegration approach. Journal of Risk and Insurance, 70(3), 489-508. https://doi.org/10.1111/1539-6975.t01-1-00061
Moreno, L. G. (2019). Notas de clase: teoría del riesgo y contingencias.
Namvar, M., Gholamian, M. R. & KhakAbi, S. (2010). A two phase clustering method for intelligent customer segmentation. 2010 International Conference on Intelligent Systems, Modelling and Simulation, Liverpool, UK, pp. 215-219. https://doi.org/10.1109/ISMS.2010.48
Outreville, J. F. (1990). Whole-life insurance lapse rates and the emergency fund hypothesis. Insurance: Mathematics and Economics, 9(4), 249-255. https://doi.org/10.1016/0167-6687(90)90002-U
Outreville, J. F. (2013). The relationship between insurance and economic development: 85 empirical papers for a review of the literature. Risk Management and Insurance Review, 16(1), 71-122. https://doi.org/10.1111/j.1540-6296.2012.01219.x
Pinquet, J., Guillén, M. & Ayuso, M. (2011). Commitment and lapse behavior in long-term insurance: a case study. Journal of Risk and Insurance, 78(4), 983-1002. https://doi.org/10.1111/j.1539-6975.2011.01420.x
Pölsterl, S. (2020). Scikit-survival: a library for time-to-event analysis built on top of scikit-learn. The Journal of Machine Learning Research, 21, 1-6. https://jmlr.org/papers/volume21/20-729/20-729.pdf
Ramchandani, P., Paich, M. & Rao, A. (2017). Incorporating learning into decision making in agent based models. In E. Oliveira, J. Gama, Z. Vale, H. Lopes (Eds.), Progress in Artificial Intelligence: 18th EPIA Conference on Artificial Intelligence, EPIA 2017, Porto, Portugal, (pp. 789-800). https://doi.org/10.1007/978-3-319-65340-2_64
Richman, R. (2018). AI in actuarial science. SSRN. http://dx.doi.org/10.2139/ssrn.3218082
Rozar, T., Scott, R. & Susan, W. (2010). Report on the lapse and mortality experience of post-level premium period term plans.
Rudin, C. (2012). 15.097 Lecture 13: Kernels. MIT Open Course Ware. http://ocw.mit.edu/courses/15-097-prediction-machine-learning-and-statistics-spring-2012/resources/mit15_097s12_lec13/
Tang, S. & Yang, Y. (2021). Why neural networks apply to scientific computing? Theoretical and Applied Mechanics Letters, 11(3), 100242. https://doi.org/10.1016/j.taml.2021.100242
Tsai, C., Kuo, W. & Chiang, D. M. (2009). The distributions of policy reserves considering the policy-year structures of surrender rates and expense ratios. Journal of Risk and Insurance, 76(4), 909-931. https://doi.org/10.1111/j.1539-6975.2009.01324.x
Weindorfer, B. (2012). QIS5: a review of the results for EEA Member States, Austria and Germany. https://www.fh-vie.ac.at/uploads/WP-070_2012.pdf
Xong, L. J. & Kang, H. M. (2019). A comparison of classification models for life insurance lapse risk. International Journal of Recent Technology and Engineering, 7(5S), 245-250.
Zaki, M. & Meira, W. (2014). Data mining and Machine Learning: fundamental concepts and algorithms. (2nd ed.). Cambridge University Press. https://www.cambridge.org/co/academic/subjects/computer-science/knowledge-management-databases-and-data-mining/data-mining-and-machine-learning-fundamental-concepts-and-algorithms-2nd-edition?format=HB&isbn=9781108473989
Zhu, H., Zeng, H., Liu, J. & Zhang, X. (2021). Logish: A new nonlinear nonmonotonic activation function for convolutional neural network. Neurocomputing, 458, 490-499. https://doi.org/10.1016/j.neucom.2021.06.067