Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Bücher
Zeitschriften
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
ATZ-Fachkongress

Chassis.tech plus 2024


4 Kongresse in einer Veranstaltung

Treffen Sie in München die Fachleute von Chassis, Lenkung, Bremsen sowie Reifen/Räder.
Erweiterte Suche
Anmelden
nach oben
The Journal of Supercomputing

17.05.2024

A hybrid recursive direct system for multi-step mortality rate forecasting

verfasst von: Filipe Coelho de Lima Duarte, Paulo S. G. de Mattos Neto, Paulo Renato Alves Firmino

Erschienen in: The Journal of Supercomputing

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Forecasting mortality is challenging. In general, mortality rate forecasting exercises have been based on the supposition that predictors’ residuals are random noise. However, issues regarding model selection, misspecification, or the dynamic behavior of the temporal phenomenon lead to biased or underperformed single models. Residual series might present temporal patterns that can still be used to improve the forecasting system. This paper proposes a new recursive direct multi-step Hybrid System for Mortality Forecasting (HyS-MF) that combines the Autoregressive Integrated Moving Average (ARIMA) with Neural Basis Expansion for Time Series Forecasting (N-BEATS). HyS-MF employs (i) ARIMA to model and forecast the mortality rate time series with a recursive approach and (ii) N-BEATS with the direct multi-step approach to learn and forecast the residuals of the linear predictor. The final output is generated by summing ARIMA with the N-BEATS forecasts in each time horizon. HyS-MF achieved an average Mean Absolute Percentage Error (MAPE) less than 1.34% considering all prediction horizons, beating statistical techniques, machine learning, deep learning models, and hybrid systems considering 101 different time series from the French population mortality rate.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren
Literatur
1.
Bravo J (2007) Tábuas de mortalidade contemporâneas e prospectivas: Modelos estocásticos, aplicações actuariais e cobertura do risco de longevidade. PhD thesis, Universidade de Évora
2.
Shen Y, Yang X, Liu H et al (2024) Advancing mortality rate prediction in European population clusters: integrating deep learning and multiscale analysis. Sci Rep 14(1):6255CrossRef
3.
van de Walk F (2017) Infant mortality and the european demographic transition. In: Watkins SC (ed) The decline of fertility in Europe. Princeton University Press, New Jersey, pp 201–233
4.
5.
Kruk ME, Gage AD, Joseph NT et al (2018) Mortality due to low-quality health systems in the universal health coverage era: a systematic analysis of amenable deaths in 137 countries. The Lancet 392(10160):2203–2212CrossRef
6.
Chen N, Pan J (2022) The causal effect of delivery volume on severe maternal morbidity: an instrumental variable analysis in sichuan, china. BMJ Glob Health 7(5):e008428CrossRef
7.
Luy M, Di Giulio P, Di Lego V et al (2020) Life expectancy: frequently used, but hardly understood. Gerontology 66(1):95–104CrossRef
8.
Bravo JM (2021) Forecasting mortality rates with recurrent neural networks: a preliminary investigation using portuguese data. In: CAPSI 2021 Proceedings
9.
Nigri A, Levantesi S, Aburto JM (2022) Leveraging deep neural networks to estimate age-specific mortality from life expectancy at birth. Demogr Res 47:199–232CrossRef
10.
Carone G, Eckefeldt P, Giamboni L, et al (2016) Pension reforms in the EU since the early 2000’s: achievements and challenges ahead. European economy discussion paper
11.
Janssen F (2018) Advances in mortality forecasting: introduction. Genus 74(1):21CrossRef
12.
Olivieri A (2001) Uncertainty in mortality projections: an actuarial perspective. Insur: Math Econ 29(2):231–245
13.
Shi Y (2021) Forecasting mortality rates with the penalized exponential smoothing state space model. J Operat Res Soci 73(5):955–968CrossRef
14.
Hyndman RJ, Shahid Ullah M (2007) Robust forecasting of mortality and fertility rates: a functional data approach. Comput Stat Data Anal 51(10):4942–4956MathSciNetCrossRef
15.
Vanella P, Deschermeier P, Wilke CB (2020) An overview of population projections-methodological concepts, international data availability, and use cases. Forecasting 2(3):346–363CrossRef
16.
Dushi I, Friedberg L, Webb T (2010) The impact of aggregate mortality risk on defined benefit pension plans. J Pension Econ Finance 9(4):481–503CrossRef
17.
Mitchell D, Brockett P, Mendoza-Arriaga R et al (2013) Modeling and forecasting mortality rates. Insur: Math Econ 52(2):275–285MathSciNet
18.
Wang J, Wen L, Xiao L et al (2024) Time-series forecasting of mortality rates using transformer. Scand Actuar J 2:109–123MathSciNetCrossRef
19.
Bi L, Fili M, Hu G (2022) Covid-19 forecasting and intervention planning using gated recurrent unit and evolutionary algorithm. Neural Computing and Applications pp 1–19
20.
Wu R, Wang B (2018) Gaussian process regression method for forecasting of mortality rates. Neurocomputing 316:232–239CrossRef
21.
Feng L, Shi Y (2018) Forecasting mortality rates: multivariate or univariate models? J Popul Res 35(3):289–318CrossRef
22.
Lee RD, Carter LC (1992) Modeling and forecasting US mortality. J Am Stat Associat 87(419):659–671
23.
Booth H, Maindonald J, Smith L (2002) Applying Lee-Carter under conditions of variable mortality decline. Popul Stud 56(3):325–336CrossRef
24.
Deprez P, Shevchenko PV, Wüthrich MV (2017) Machine learning techniques for mortality modeling. Eur Actuar J 7(2):337–352MathSciNetCrossRef
25.
Nigri A, Levantesi S, Marino M et al (2019) A deep learning integrated lee-carter model. Risks 7(1):33CrossRef
26.
McNown R, Rogers A (1989) Forecasting mortality: a parameterized time series approach. Demography 26(4):645–660CrossRef
27.
de Mattos Neto PS, Cavalcanti GD, Madeiro F (2017) Nonlinear combination method of forecasters applied to PM time series. Patt Recogn Lett 95:65–72CrossRef
28.
Richman R, Wüthrich MV (2018) A neural network extension of the Lee-Carter Model to multiple populations. SSRN
29.
Petneházi G, Gáll J (2019) Mortality rate forecasting: can recurrent neural networks beat the lee-carter model? arXiv preprint arXiv:​1909.​05501
30.
Perla F, Richman R, Scognamiglio S et al (2021) Time-series forecasting of mortality rates using deep learning. Scand Actuar J 2021(7):572–598MathSciNetCrossRef
31.
Hong WH, Yap JH, Selvachandran G et al (2021) Forecasting mortality rates using hybrid lee-carter model, artificial neural network and random forest. Complex Intell Syst 7:163–189CrossRef
32.
Chen Y, Khaliq AQ (2022) Comparative study of mortality rate prediction using data-driven recurrent neural networks and the lee-carter model. Big Data Cognit Comput 6(4):134CrossRef
33.
Roshani A, Izadi M, Khaledi BE (2022) Transformer self-attention network for forecasting mortality rates. J Iran Stat Soci 21(1):81–103MathSciNet
34.
de Mattos Neto PS, Cavalcanti GD, de Santos Júnior ODS et al (2022) Hybrid systems using residual modeling for sea surface temperature forecasting. Scientific Reports 12(1):487CrossRef
35.
Pang X, Zhou Y, Wang P et al (2020) An innovative neural network approach for stock market prediction. J Supercomput 76:2098–2118CrossRef
36.
Bravo JM (2021) Forecasting longevity for financial applications: a first experiment with deep learning methods. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Springer, pp 232–249
37.
Bravo JM, Santos V (2021) Backtesting recurrent neural networks with gated recurrent unit: probing with chilean mortality data. In: International Conference on Computer Science. Springer, Electronics and Industrial Engineering (CSEI), pp 159–174
38.
Jackins V, Vimal S, Kaliappan M et al (2021) Ai-based smart prediction of clinical disease using random forest classifier and naive bayes. J Supercomput 77(5):5198–5219CrossRef
39.
Ashofteh A, Bravo JM, Ayuso M (2022) An ensemble learning strategy for panel time series forecasting of excess mortality during the covid-19 pandemic. Appl Soft Comput 128:109422CrossRef
40.
Xu Y, Wang E, Yang Y et al (2021) A unified collaborative representation learning for neural-network based recommender systems. IEEE Trans Knowl Data Eng 34(11):5126–5139CrossRef
41.
Kavianpour P, Kavianpour M, Jahani E et al (2023) A cnn-bilstm model with attention mechanism for earthquake prediction. J Supercomput 79(17):19194–19226CrossRef
42.
Santos WR, Sampaio AR Jr, Rosa NS et al (2024) Microservices performance forecast using dynamic multiple predictor systems. Eng Appl Artif Intell 129:107649CrossRef
43.
Zhang G (2003) Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50:159–175CrossRef
44.
Khashei M, Bijari M (2011) A novel hybridization of artificial neural networks and ARIMA models for time series forecasting. Appl Soft Comput 11(2):2664–2675CrossRef
45.
Meng H, Han L, Hou L (2022) An ensemble learning-based short-term load forecasting on small datasets. In: 2022 IEEE 33rd Annual International Symposium on Personal. Indoor and Mobile Radio Communications (PIMRC), IEEE, pp 346–350
46.
de Mattos Neto PS, de Oliveira JF, de O Santos Júnior DS, et al (2021) An adaptive hybrid system using deep learning for wind speed forecasting. Inform Sci 581:495–514
47.
48.
Shaikhina T, Lowe D, Daga S et al (2015) Machine learning for predictive modelling based on small data in biomedical engineering. IFAC-PapersOnLine 48(20):469–474CrossRef
49.
D’souza RN, Huang PY, Yeh FC (2020) Structural analysis and optimization of convolutional neural networks with a small sample size. Sci Rep 10(1):834CrossRef
50.
Meroni M, Waldner F, Seguini L et al (2021) Yield forecasting with machine learning and small data: what gains for grains? Agric For Meteorol 308:108555CrossRef
51.
Oreshkin BN, Carpov D, Chapados N, et al. (2019) N-beats: neural basis expansion analysis for interpretable time series forecasting. arXiv preprint arXiv:​1905.​10437
52.
Oreshkin BN, Dudek G, Pełka P et al (2021) N-beats neural network for mid-term electricity load forecasting. Appl Energy 293:116918CrossRef
53.
Human Mortality Database (2021) University of California, Berkeley (USA), and Max Plank Institute for Demographic Research (Germany). Available at www.​mortality.​org; accessed on 04/20/2021
54.
Hyndman RJ, Koehler AB, Snyder RD et al (2002) A state space framework for automatic forecasting using exponential smoothing methods. Int J Forecast 18(3):439–454CrossRef
55.
De Livera AM, Hyndman RJ, Snyder RD (2011) Forecasting time series with complex seasonal patterns using exponential smoothing. J Am Stat Assoc 106(496):1513–1527MathSciNetCrossRef
56.
Box GE, Jenkins GM, Reinsel GC et al (2015) Time series analysis: forecasting and control. Wiley, Hoboken
57.
Vaswani A, Shazeer N, Parmar N, et al. (2017) Attention is all you need. Advances in neural information processing systems 30
58.
Wu H, Xu J, Wang J et al (2021) Autoformer: decomposition transformers with auto-correlation for long-term series forecasting. Adv Neural Inf Process Syst 34:22419–22430
59.
Zhou T, Ma Z, Wen Q, et al. (2022) Fedformer: fenhanced decomposed transformer for long-term series forecasting. In: International Conference on Machine Learning, PMLR, pp 27268–27286
60.
Challu C, Olivares KG, Oreshkin BN, et al. (2023) Nhits: neural hierarchical interpolation for time series forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 6989–6997
61.
Bell WR (1997) Comparing and assessing time series methods for forecasting age-specific fertility and mortality rates. J Off Stat 13:279–303
62.
Renshaw A, Haberman S (2006) A cohort-based extension to the Lee-Carter model for mortality reduction factors. Insur: Math Econ 38(3):556–570
63.
Hyndman RJ, Booth H, Yasmeen F (2013) Coherent mortality forecasting: the product-ratio method with functional time series models. Demography 50(1):261–283CrossRef
64.
Wu R, Wang B (2019) Coherent mortality forecasting by the weighted multilevel functional principal component approach. J Appl Stat 46(10):1774–1791MathSciNetCrossRef
65.
66.
Makridakis S, Hyndman RJ, Petropoulos F (2020) Forecasting in social settings: the state of the art. Int J Forecast 36(1):15–28CrossRef
67.
Booth H, Tickle L (2008) Mortality modelling and forecasting: a review of methods. Ann Act Sci 3(1–2):3–43CrossRef
68.
Giacometti R, Bertocchi M, Rachev ST et al (2012) A comparison of the Lee-Carter model and AR-ARCH model for forecasting mortality rates. Insur: Math Econ 50(1):85–93MathSciNet
69.
Shang HL, Hyndman RJ (2017) Grouped functional time series forecasting: an application to age-specific mortality rates. J Comput Graph Stat 26(2):330–343MathSciNetCrossRef
70.
Santos JDSdO, Oliveira JFd, de Mattos Neto PSG (2019) An intelligent hybridization of ARIMA with machine learning models for time series forecasting. Knowl-Based Syst 175:72–86CrossRef
71.
Hajirahimi Z, Khashei M (2019) Hybrid structures in time series modeling and forecasting: A review. Eng Appl Artif Intell 86:83–106CrossRef
72.
Pai PF, Lin CS (2005) A hybrid ARIMA and support vector machines model in stock price forecasting. Omega 33(6):497–505CrossRef
73.
Panigrahi S, Behera HS (2017) A hybrid ETS-ANN model for time series forecasting. Eng Appl Artif Intell 66:49–59CrossRef
74.
Hajirahimi Z, Khashei M (2019) Weighted sequential hybrid approaches for time series forecasting. Physica A: Stat Mech Appl 531
75.
Babu CN, Reddy BE (2014) A moving-average filter based hybrid arima-ann model for forecasting time series data. Appl Soft Comput 23:27–38CrossRef
76.
Shi J, Guo J, Zheng S (2012) Evaluation of hybrid forecasting approaches for wind speed and power generation time series. Renew Sustain Energy Rev 16(5):3471–3480CrossRef
77.
Chakraborty T, Chattopadhyay S, Ghosh I (2019) Forecasting dengue epidemics using a hybrid methodology. Physica A 527:121266CrossRef
78.
Iftikhar H, Daniyal M, Qureshi M et al (2023) A hybrid forecasting technique for infection and death from the mpox virus. Digital Health 9:20552076231204748CrossRef
79.
Iftikhar H, Zafar A, Turpo-Chaparro JE et al (2023) Forecasting day-ahead brent crude oil prices using hybrid combinations of time series models. Mathematics 11(16):3548CrossRef
80.
Carbo-Bustinza N, Iftikhar H, Belmonte M et al (2023) Short-term forecasting of ozone concentration in metropolitan lima using hybrid combinations of time series models. Appl Sci 13(18):10514CrossRef
81.
Sorjamaa A, Hao J, Reyhani N et al (2007) Methodology for long-term prediction of time series. Neurocomputing 70(16–18):2861–2869CrossRef
82.
Hamzaçebi C, Akay D, Kutay F (2009) Comparison of direct and iterative artificial neural network forecast approaches in multi-periodic time series forecasting. Expert Syst Appl 36(2):3839–3844CrossRef
83.
Taieb SB, Bontempi G, Atiya AF et al (2012) A review and comparison of strategies for multi-step ahead time series forecasting based on the nn5 forecasting competition. Expert Syst Appl 39(8):7067–7083CrossRef
84.
Kline DM (2004) Methods for multi-step time series forecasting neural networks. In: Zhang GP (ed) Neural networks in business forecasting. IGI Global, Hershey, PA, USA, pp 226–250
85.
Bontempi G (2008) Long term time series prediction with multi-input multi-output local learning. In: Proceedings of the 2nd European Symposium on Time Series Prediction (TSP), ESTSP08
86.
Ming W, Bao Y, Hu Z, et al (2014) Multistep-ahead air passengers traffic prediction with hybrid arima-svms models. The Scientific World Journal 2014
87.
Taieb SB, Bontempi G, Sorjamaa A, et al. (2009) Long-term prediction of time series by combining direct and mimo strategies. In: 2009 International Joint Conference on Neural Networks, IEEE, pp 3054–3061
88.
Beyaztas U, Shang H (2022) Machine-learning-based functional time series forecasting: application to age-specific mortality rates. Forecasting 4(1):394–408CrossRef
89.
Ouyang Z, Ravier P, Jabloun M (2022) Are deep learning models practically good as promised? a strategic comparison of deep learning models for time series forecasting. In: 2022 30th European Signal Processing Conference (EUSIPCO), IEEE, pp 1477–1481
90.
Atiya A, El-Shoura S, Shaheen S et al (1999) A comparison between neural-network forecasting techniques-case study: river flow forecasting. IEEE Trans Neural Networks 10(2):402–409CrossRef
91.
Taieb SB (2014) Machine learning strategies for multi-step-ahead time series forecasting. Universit Libre de Bruxelles, Belgium pp 75–86
92.
Mendes-Moreira J, Soares C, Jorge AM et al (2012) Ensemble approaches for regression: a survey. ACM Comput Surv (csur) 45(1):1–40CrossRef
93.
Lam KK, Wang B (2021) Robust non-parametric mortality and fertility modelling and forecasting: Gaussian process regression approaches. Forecasting 3(1):207–227CrossRef
94.
da Rocha AM, Espíndola AL, Penna T (2020) Mortality curves using a bit-string aging model. Physica A 560:125134CrossRef
95.
Hyndman RJ, Booth H (2008) Stochastic population forecasts using functional data models for mortality, fertility and migration. Int J Forecast 24(3):323–342CrossRef
96.
Chandra R, Goyal S, Gupta R (2021) Evaluation of deep learning models for multi-step ahead time series prediction. IEEE Access 9:83105–83123CrossRef
97.
98.
Hyndman RJ, Khandakar Y (2008) Automatic time series forecasting: the forecast package for R. J Stat Softw 27(1):1–22
99.
100.
Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830MathSciNet
101.
102.
103.
104.
105.
de Oliveira JF, Silva EG, de Mattos Neto PS (2021) A hybrid system based on dynamic selection for time series forecasting. IEEE Trans Neural Netw Learn Syst 33(8):3251–3263MathSciNetCrossRef
106.
Kim S, Kim H (2016) A new metric of absolute percentage error for intermittent demand forecasts. Int J Forecast 32(3):669–679CrossRef
107.
Hyndman RJ, Koehler AB (2006) Another look at measures of forecast accuracy. Int J Forecast 22(4):679–688CrossRef
108.
Diebold FX, Mariano RS (1995) Comparing predictive accuracy. J Bus Econ Stat 13(3):253–263CrossRef
109.
110.
Medina MCC, de Oliveira JFL (2023) A selective hybrid system for state-of-charge forecasting of lithium-ion batteries. J Supercomput 79(14):15623–15642CrossRef
111.
Silva EG, Júunior DSdO, Cavalcanti GD, et al. (2018) Improving the accuracy of intelligent forecasting models using the perturbation theory. In: 2018 International Joint Conference on Neural Networks (IJCNN), IEEE, pp 1–7
Metadaten
Titel
A hybrid recursive direct system for multi-step mortality rate forecasting
verfasst von
Filipe Coelho de Lima Duarte
Paulo S. G. de Mattos Neto
Paulo Renato Alves Firmino
Publikationsdatum
17.05.2024
Verlag
Springer US
Erschienen in
The Journal of Supercomputing
Print ISSN: 0920-8542
Elektronische ISSN: 1573-0484
DOI
https://doi.org/10.1007/s11227-024-06182-x

Premium Partner

    Bildnachweise