A neural network extension of the Lee–Carter model to multiple populations

The Lee-Carter model is a basic approach to forecasting mortality rates of a single population. Although extensions of the Lee-Carter model to forecasting rates for multiple populations have recently been proposed, the structure of these extended models is hard to justify and the models are often difficult to calibrate, relying on customized optimization schemes. Based on the paradigm of representation learning, we extend the Lee-Carter model to multiple populations using neural networks, which automatically select an optimal model structure. We fit this model to mortality rates since 1950 for all countries in the Human Mortality Database and observe that the out-of-sample forecasting performance of the model is highly competitive.

[1]  Galit Shmueli,et al.  To Explain or To Predict? , 2010, 1101.0891.

[2]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5]  Nan Li,et al.  Coherent mortality forecasts for a group of populations: An extension of the lee-carter method , 2005, Demography.

[6]  I. Currie.  On fitting generalized linear and non-linear models of mortality , 2016 .

[7]  Ronald Richman,et al.  AI in Actuarial Science , 2018 .

[8]  Yoshua Bengio,et al.  A Neural Probabilistic Language Model , 2003, J. Mach. Learn. Res..

[9]  Dmitri Jdanov,et al.  Human Mortality Database , 2019, Encyclopedia of Gerontology and Population Aging.

[10]  Torsten Kleinow,et al.  A common age effect model for the mortality of multiple populations , 2015 .

[11]  David Blake,et al.  Backtesting Stochastic Mortality Models , 2010 .

[12]  François Chollet,et al.  Keras: The Python Deep Learning library , 2018 .

[13]  Ronald Lee,et al.  Modeling and forecasting U. S. mortality , 1992 .

[14]  T. Kleinow,et al.  Multi-population mortality models: fitting, forecasting and comparisons , 2017 .

[15]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[16]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[17]  Ivan Luciano Danesi,et al.  Forecasting mortality in subpopulations using Lee–Carter type models: A comparison , 2015 .

[18]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[19]  Kevin Dowd,et al.  A Two-Factor Model for Stochastic Mortality With Parameter Uncertainty: Theory and Calibration , 2006 .

[20]  Michel Denuit,et al.  A Poisson log-bilinear regression approach to the construction of projected lifetables , 2002 .

[21]  David Firth,et al.  Generalized nonlinear models in R: An overview of the gnm package , 2007 .

[22]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[23]  Mario V. Wuthrich,et al.  Data Analytics for Non-Life Insurance Pricing , 2019 .

[24]  Dmitri A. Jdanov,et al.  Human Mortality Database , 2019, Encyclopedia of Gerontology and Population Aging.

[25]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[26]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[27]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Fotios Petropoulos,et al.  forecast: Forecasting functions for time series and linear models , 2018 .

[29]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[30]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[31]  Pietro Millossovich,et al.  Sex-specific mortality forecasting for UK countries: a coherent approach , 2018, European Actuarial Journal.

[32]  V. Kaishev,et al.  A COMPARATIVE STUDY OF TWO-POPULATION MODELS FOR THE ASSESSMENT OF BASIS RISK IN LONGEVITY HEDGES , 2017 .

[33]  Cheng Guo,et al.  Entity Embeddings of Categorical Variables , 2016, ArXiv.