{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T16:40:34Z","timestamp":1772728834303,"version":"3.50.1"},"reference-count":38,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T00:00:00Z","timestamp":1668038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>The Lee\u2013Carter model could be considered as one of the most important mortality prediction models among stochastic models in the field of mortality. With the recent developments of machine learning and deep learning, many studies have applied deep learning approaches to time series mortality rate predictions, but most of them only focus on a comparison between the Long Short-Term Memory and the traditional models. In this study, three different recurrent neural networks, Long Short-Term Memory, Bidirectional Long Short-Term Memory, and Gated Recurrent Unit, are proposed for the task of mortality rate prediction. Different from the standard country level mortality rate comparison, this study compares the three deep learning models and the classic Lee\u2013Carter model on nine divisions\u2019 yearly mortality data by gender from 1966 to 2015 in the United States. With the out-of-sample testing, we found that the Gated Recurrent Unit model showed better average MAE and RMSE values than the Lee\u2013Carter model on 72.2% (13\/18) and 67.7% (12\/18) of the database, respectively, while the same measure for the Long Short-Term Memory model and Bidirectional Long Short-Term Memory model are 50%\/38.9% (MAE\/RMSE) and 61.1%\/61.1% (MAE\/RMSE), respectively. If we consider forecasting accuracy, computing expense, and interpretability, the Lee\u2013Carter model with ARIMA exhibits the best overall performance, but the recurrent neural networks could also be good candidates for mortality forecasting for divisions in the United States.<\/jats:p>","DOI":"10.3390\/bdcc6040134","type":"journal-article","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T19:16:23Z","timestamp":1668107783000},"page":"134","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Comparative Study of Mortality Rate Prediction Using Data-Driven Recurrent Neural Networks and the Lee\u2013Carter Model"],"prefix":"10.3390","volume":"6","author":[{"given":"Yuan","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Mathematical Sciences, Middle Tennessee State University, Murfreesboro, TN 37132-0001, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdul Q. M.","family":"Khaliq","sequence":"additional","affiliation":[{"name":"Department of Mathematical Sciences, Middle Tennessee State University, Murfreesboro, TN 37132-0001, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,10]]},"reference":[{"key":"ref_1","first-page":"659","article-title":"Modeling and Forecasting U.S. Mortality","volume":"87","author":"Lee","year":"1992","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/S0167-6687(02)00185-3","article-title":"A Poisson log-bilinear regression approach to the construction of projected lifetables","volume":"31","author":"Brouns","year":"2002","journal-title":"Insur. Math. Econ."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"4942","DOI":"10.1016\/j.csda.2006.07.028","article-title":"Robust forecasting of mortality and fertility rates: A functional data approach","volume":"51","author":"Hyndman","year":"2007","journal-title":"Comput. Stat. Data Anal."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1017\/asb.2019.20","article-title":"Dynamic principal component regression: Application to age-specific mortality forecasting","volume":"49","author":"Shang","year":"2019","journal-title":"ASTIN Bull."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1111\/j.1539-6975.2006.00195.x","article-title":"A Two-Factor Model for Stochastic Mortality with Parameter Uncertainty: Theory and Calibration","volume":"73","author":"Cairns","year":"2006","journal-title":"J. Risk Insur."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"556","DOI":"10.1016\/j.insmatheco.2005.12.001","article-title":"A cohort-based extension to the Lee\u2013Carter model for mortality reduction factors","volume":"38","author":"Renshaw","year":"2006","journal-title":"Insur. Math. Econ."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1007\/s13385-017-0152-4","article-title":"Machine learning techniques for mortality modeling","volume":"7","author":"Deprez","year":"2017","journal-title":"Eur. Actuar. J."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Levantesi, S., and Pizzorusso, V. (2019). Application of Machine Learning to Mortality Modeling and Forecasting. Risks, 7.","DOI":"10.3390\/risks7010026"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Hassani, H., Unger, S., and Beneki, C. (2020). Big Data and Actuarial Science. Big Data Cogn. Comput., 4.","DOI":"10.3390\/bdcc4040040"},{"key":"ref_10","unstructured":"Richman, R. (2022, October 10). AI in Actuarial Science. Available online: https:\/\/ssrn.com\/abstract=3218082."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1017\/asb.2017.45","article-title":"A neural-network analyzer for mortality forecast","volume":"48","author":"Hainaut","year":"2018","journal-title":"ASTIN Bull."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1080\/03461238.2020.1867232","article-title":"Time-series forecasting of mortality rates using deep learning","volume":"2021","author":"Perla","year":"2021","journal-title":"Scand. Actuar. J."},{"key":"ref_13","unstructured":"Human Mortality Database (2022, October 10). University of California, Berkeley (USA) and Max Planck Institute for Demographic Research (Germany). Available online: http:\/\/www.mortality.org."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Nigri, A., Levantesi, S., Marino, M., Scognamiglio, S., and Perla, F. (2019). A Deep Learning Integrated Lee\u2013Carter Model. Risks, 7.","DOI":"10.3390\/risks7010033"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1080\/03461238.2020.1814855","article-title":"Life expectancy and lifespan disparity forecasting: A long short-term memory approach","volume":"2021","author":"Nigri","year":"2020","journal-title":"Scand. Actuar. J."},{"key":"ref_16","unstructured":"Marino, M., and Levantesi, S. (2022, October 10). Measuring Longevity Risk through a Neural Network Lee-Carter Model. Available online: https:\/\/ssrn.com\/abstract=3599821."},{"key":"ref_17","unstructured":"Richman, R., and Wuthrich, M.V. (2022, October 10). Lee and Carter Go Machine Learning: Recurrent Neural Networks. Available online: https:\/\/ssrn.com\/abstract=3441030."},{"key":"ref_18","unstructured":"Castellani, G., Fiore, U., Marino, Z., Passalacqua, L., Perla, F., Scognamiglio, S., and Zanetti, P. (2022, October 10). An Investigation of Machine Learning Approaches in the Solvency II Valuation Framework. Available online: https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=3303296."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1007\/s40747-020-00185-w","article-title":"Forecasting mortality rates using hybrid Lee\u2013Carter model, artificial neural network and random forest","volume":"7","author":"Hong","year":"2021","journal-title":"Complex Intell. Syst."},{"key":"ref_20","unstructured":"Richman, R., and Wuthrich, M.V. (2022, October 10). A Neural Network Extension of the Lee-Carter Model to Multiple Populations. Available online: https:\/\/ssrn.com\/abstract=3270877."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Gabrielli, A., and W\u00fcthrich, M.V. (2018). An Individual Claims History Simulation Machine. Risks, 6.","DOI":"10.3390\/risks6020029"},{"key":"ref_22","unstructured":"Petneh\u00e1zi, G., and G\u00e1ll, J. (2022). Mortality rate forecasting: Can recurrent neural networks beat the Lee-Carter model?. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hocreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv.","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref_26","unstructured":"Chung, J., Gulcehre, C., Cho, K., and Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v027.i03","article-title":"Automatic Time Series Forecasting: The forecast Package for R","volume":"27","author":"Hyndman","year":"2008","journal-title":"J. Stat. Softw."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"527","DOI":"10.4054\/DemRes.2017.37.17","article-title":"Coherent forecasts of mortality with compositional data analysis","volume":"37","author":"Oeppen","year":"2017","journal-title":"Demogr. Res."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"289","DOI":"10.4054\/DemRes.2006.15.9","article-title":"Lee-Carter mortality forecasting: A multi-country comparison of variants and extensions","volume":"15","author":"Booth","year":"2006","journal-title":"Demogr. Res."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/j.ijforecast.2008.02.009","article-title":"Stochastic population forecasts using functional data models for mortality, fertility and migration","volume":"24","author":"Hyndman","year":"2008","journal-title":"Int. J. Forecast."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1038\/35015561","article-title":"A universal pattern of mortality decline in the G7 countries","volume":"405","author":"Tuljapurkar","year":"2000","journal-title":"Nature"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1353\/dem.2001.0036","article-title":"Evaluating the Performance of the Lee-Carter Method for Forecasting Mortality","volume":"38","author":"Lee","year":"2001","journal-title":"Demography"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"54033","DOI":"10.1109\/ACCESS.2018.2871713","article-title":"Calibrated Prediction Intervals for Neural Network Regressors","volume":"6","author":"Keren","year":"2018","journal-title":"IEEE Access"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.1109\/TNN.2011.2162110","article-title":"Comprehensive Review of Neural Network-Based Prediction Intervals and New Advances","volume":"22","author":"Khosravi","year":"2011","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_35","first-page":"54","article-title":"Bootstrap methods for standard errors, confidence intervals, and other measures of statistical accuracy","volume":"1","author":"Efron","year":"1986","journal-title":"Stat. Sci."},{"key":"ref_36","unstructured":"Dietterich, T. (2002). Ensemble learning. The Handbook of Brain Theory and Neural Networks, MIT Press."},{"key":"ref_37","unstructured":"Heskes, T. (1997). Practical confidence and prediction intervals. Advances in Neural Information Processing Systems, MIT Press."},{"key":"ref_38","unstructured":"Petneh\u00e1zi, G. (2018). Recurrent Neural Networks for Time Series Forecasting. arXiv."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/6\/4\/134\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:14:04Z","timestamp":1760145244000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/6\/4\/134"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,10]]},"references-count":38,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["bdcc6040134"],"URL":"https:\/\/doi.org\/10.3390\/bdcc6040134","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,10]]}}}