IDEAS home Printed from https://ideas.repec.org/a/gam/jforec/v4y2021i1p1-25d708917.html
   My bibliography  Save this article

A Statistics and Deep Learning Hybrid Method for Multivariate Time Series Forecasting and Mortality Modeling

Author

Listed:
  • Thabang Mathonsi

    (School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg 2000, South Africa
    These authors contributed equally to the conceptualisation and presentation of this work.)

  • Terence L. van Zyl

    (Institute for Intelligent Systems, University of Johannesburg, Johannesburg 2092, South Africa
    These authors contributed equally to the conceptualisation and presentation of this work.)

Abstract

Hybrid methods have been shown to outperform pure statistical and pure deep learning methods at forecasting tasks and quantifying the associated uncertainty with those forecasts (prediction intervals). One example is Exponential Smoothing Recurrent Neural Network (ES-RNN), a hybrid between a statistical forecasting model and a recurrent neural network variant. ES-RNN achieves a 9.4% improvement in absolute error in the Makridakis-4 Forecasting Competition. This improvement and similar outperformance from other hybrid models have primarily been demonstrated only on univariate datasets. Difficulties with applying hybrid forecast methods to multivariate data include (i) the high computational cost involved in hyperparameter tuning for models that are not parsimonious, (ii) challenges associated with auto-correlation inherent in the data, as well as (iii) complex dependency (cross-correlation) between the covariates that may be hard to capture. This paper presents Multivariate Exponential Smoothing Long Short Term Memory (MES-LSTM), a generalized multivariate extension to ES-RNN, that overcomes these challenges. MES-LSTM utilizes a vectorized implementation. We test MES-LSTM on several aggregated coronavirus disease of 2019 (COVID-19) morbidity datasets and find our hybrid approach shows consistent, significant improvement over pure statistical and deep learning methods at forecast accuracy and prediction interval construction.

Suggested Citation

  • Thabang Mathonsi & Terence L. van Zyl, 2021. "A Statistics and Deep Learning Hybrid Method for Multivariate Time Series Forecasting and Mortality Modeling," Forecasting, MDPI, vol. 4(1), pages 1-25, December.
    • Handle: RePEc:gam:jforec:v:4:y:2021:i:1:p:1-25:d:708917
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2571-9394/4/1/1/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2571-9394/4/1/1/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Smyl, Slawek, 2020. "A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting," International Journal of Forecasting, Elsevier, vol. 36(1), pages 75-85.
    2. Hyndman, Rob J. & Koehler, Anne B. & Snyder, Ralph D. & Grose, Simone, 2002. "A state space framework for automatic forecasting using exponential smoothing methods," International Journal of Forecasting, Elsevier, vol. 18(3), pages 439-454.
    3. Lim, Bryan & Arık, Sercan Ö. & Loeff, Nicolas & Pfister, Tomas, 2021. "Temporal Fusion Transformers for interpretable multi-horizon time series forecasting," International Journal of Forecasting, Elsevier, vol. 37(4), pages 1748-1764.
    4. Makridakis, Spyros & Spiliotis, Evangelos & Assimakopoulos, Vassilios, 2020. "The M4 Competition: 100,000 time series and 61 forecasting methods," International Journal of Forecasting, Elsevier, vol. 36(1), pages 54-74.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Spiliotis, Evangelos & Makridakis, Spyros & Kaltsounis, Anastasios & Assimakopoulos, Vassilios, 2021. "Product sales probabilistic forecasting: An empirical evaluation using the M5 competition data," International Journal of Production Economics, Elsevier, vol. 240(C).
    2. Winita Sulandari & Yudho Yudhanto & Sri Subanti & Crisma Devika Setiawan & Riskhia Hapsari & Paulo Canas Rodrigues, 2023. "Comparing the Simple to Complex Automatic Methods with the Ensemble Approach in Forecasting Electrical Time Series Data," Energies, MDPI, vol. 16(22), pages 1-16, November.
    3. Makridakis, Spyros & Spiliotis, Evangelos & Assimakopoulos, Vassilios & Chen, Zhi & Gaba, Anil & Tsetlin, Ilia & Winkler, Robert L., 2022. "The M5 uncertainty competition: Results, findings and conclusions," International Journal of Forecasting, Elsevier, vol. 38(4), pages 1365-1385.
    4. Semenoglou, Artemios-Anargyros & Spiliotis, Evangelos & Makridakis, Spyros & Assimakopoulos, Vassilios, 2021. "Investigating the accuracy of cross-learning time series forecasting methods," International Journal of Forecasting, Elsevier, vol. 37(3), pages 1072-1084.
    5. Jennifer L. Castle & Jurgen A. Doornik & David F. Hendry, 2021. "Forecasting Principles from Experience with Forecasting Competitions," Forecasting, MDPI, vol. 3(1), pages 1-28, February.
    6. Kang, Yanfei & Spiliotis, Evangelos & Petropoulos, Fotios & Athiniotis, Nikolaos & Li, Feng & Assimakopoulos, Vassilios, 2021. "Déjà vu: A data-centric forecasting approach through time series cross-similarity," Journal of Business Research, Elsevier, vol. 132(C), pages 719-731.
    7. Petropoulos, Fotios & Apiletti, Daniele & Assimakopoulos, Vassilios & Babai, Mohamed Zied & Barrow, Devon K. & Ben Taieb, Souhaib & Bergmeir, Christoph & Bessa, Ricardo J. & Bijak, Jakub & Boylan, Joh, 2022. "Forecasting: theory and practice," International Journal of Forecasting, Elsevier, vol. 38(3), pages 705-871.
      • Fotios Petropoulos & Daniele Apiletti & Vassilios Assimakopoulos & Mohamed Zied Babai & Devon K. Barrow & Souhaib Ben Taieb & Christoph Bergmeir & Ricardo J. Bessa & Jakub Bijak & John E. Boylan & Jet, 2020. "Forecasting: theory and practice," Papers 2012.03854, arXiv.org, revised Jan 2022.
    8. Van Belle, Jente & Crevits, Ruben & Verbeke, Wouter, 2023. "Improving forecast stability using deep learning," International Journal of Forecasting, Elsevier, vol. 39(3), pages 1333-1350.
    9. Makridakis, Spyros & Spiliotis, Evangelos & Assimakopoulos, Vassilios, 2022. "Predicting/hypothesizing the findings of the M5 competition," International Journal of Forecasting, Elsevier, vol. 38(4), pages 1337-1345.
    10. Bojer, Casper Solheim & Meldgaard, Jens Peder, 2021. "Kaggle forecasting competitions: An overlooked learning opportunity," International Journal of Forecasting, Elsevier, vol. 37(2), pages 587-603.
    11. Fantazzini, Dean, 2020. "Short-term forecasting of the COVID-19 pandemic using Google Trends data: Evidence from 158 countries," Applied Econometrics, Russian Presidential Academy of National Economy and Public Administration (RANEPA), vol. 59, pages 33-54.
    12. Nghia Chu & Binh Dao & Nga Pham & Huy Nguyen & Hien Tran, 2022. "Predicting Mutual Funds' Performance using Deep Learning and Ensemble Techniques," Papers 2209.09649, arXiv.org, revised Jul 2023.
    13. Ruben Loaiza‐Maya & Gael M. Martin & David T. Frazier, 2021. "Focused Bayesian prediction," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 36(5), pages 517-543, August.
    14. Bojer, Casper Solheim, 2022. "Understanding machine learning-based forecasting methods: A decomposition framework and research opportunities," International Journal of Forecasting, Elsevier, vol. 38(4), pages 1555-1561.
    15. Makridakis, Spyros & Hyndman, Rob J. & Petropoulos, Fotios, 2020. "Forecasting in social settings: The state of the art," International Journal of Forecasting, Elsevier, vol. 36(1), pages 15-28.
    16. Sbrana, Giacomo & Silvestrini, Andrea, 2023. "The RWDAR model: A novel state-space approach to forecasting," International Journal of Forecasting, Elsevier, vol. 39(2), pages 922-937.
    17. Makridakis, Spyros & Spiliotis, Evangelos & Assimakopoulos, Vassilios, 2020. "The M4 Competition: 100,000 time series and 61 forecasting methods," International Journal of Forecasting, Elsevier, vol. 36(1), pages 54-74.
    18. Qi, Lingzhi & Li, Xixi & Wang, Qiang & Jia, Suling, 2023. "fETSmcs: Feature-based ETS model component selection," International Journal of Forecasting, Elsevier, vol. 39(3), pages 1303-1317.
    19. Gonca Gürses-Tran & Antonello Monti, 2022. "Advances in Time Series Forecasting Development for Power Systems’ Operation with MLOps," Forecasting, MDPI, vol. 4(2), pages 1-24, May.
    20. Montero-Manso, Pablo & Hyndman, Rob J., 2021. "Principles and algorithms for forecasting groups of time series: Locality and globality," International Journal of Forecasting, Elsevier, vol. 37(4), pages 1632-1653.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jforec:v:4:y:2021:i:1:p:1-25:d:708917. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.