Skip to main content
SpringerLink
Log in

A novel multi-step forecasting strategy for enhancing deep learning models’ performance

  • S.I.: Deep learning modelling in real life: (Anomaly Detection, Biomedical, Concept Analysis, Finance, Image analysis, Recommendation)
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Multi-step forecasting is considered as an open challenge in time-series analysis. Although several approaches were proposed to address this complex prediction problem, none of them could secure the development of an efficient as well as a reliable multi-step forecasting model. In this research, we present a novel strategy for the development of accurate, robust and reliable multi-step deep learning models. The proposed strategy is based on a sophisticated algorithmic framework, which is able to process, transform and deliver “high-quality” and “suitable” time-series training data. The suitability of the transformed data is secured by taking into consideration and exploiting the dynamics and the sampling of the time-series in conjunction with the forecasting horizon as well as the imposition of the stationarity property. The conducted numerical experiments performed on challenging real-world time-series datasets from the application domains: finance, commodity, climate and air quality, which demonstrate the efficacy, robustness and reliability of the proposed multi-step strategy.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Notes

  1. In most real-world applications, the order of integration is either I(0) or I(1); It’s extremely rare to see values for d that are 2 or more [7].

References

  1. An NH, Anh DT (2015) Comparison of strategies for multi-step-ahead prediction of time series using neural network. In 2015 International Conference on Advanced Computing and Applications (ACOMP), pages 142–149. IEEE

  2. Atienza R (2018) Advanced Deep Learning with Keras: apply deep learning techniques, autoencoders, GANs, variational autoencoders, deep reinforcement learning, policy gradients, and more. Packt Publishing Ltd

  3. Maiorino BE, Kampffmeyer MC, Jenssen AR (2017) Recurrent neural networks for short-term load forecasting: an overview and comparative analysis. Springer, Berlin

    Google Scholar 

  4. Bontempi G (2008) Long term time series prediction with multi-input multi-output local learning. Proc. 2nd ESTSP, pages 145–154

  5. Box GEP, Jenkins GM, Reinsel GC, Ljung GM (2015) Time series analysis: forecasting and control. Wiley, Hoboken

    MATH  Google Scholar 

  6. Brockwell PJ, Davis RA (2016) Introduction to time series and forecasting. Springer, Berlin

    Book  MATH  Google Scholar 

  7. Burke S, Hunter J (2005) Modelling non-stationary economic time series: a multivariate approach. Springer, Berlin

    Book  Google Scholar 

  8. Leopoldo C, Stefano G, Francesco R (2019) Forecasting cryptocurrencies under model and parameter instability. Int J Forecast 35(2):485–501

    Article  Google Scholar 

  9. Cen Z, Wang J (2018) Forecasting neural network model with novel CID learning rate and EEMD algorithms on energy market. Neurocomputing 317:168–178

    Article  Google Scholar 

  10. Chen M, Wu L (2021) A dropout prediction method based on time series model in MOOCs. In Journal of Physics: Conference Series, 1774: 012065. IOP Publishing

  11. Cheng CH, Yang JH (2018) Fuzzy time-series model based on rough set rule induction for forecasting stock price. Neurocomputing 302:33–45

    Article  Google Scholar 

  12. Cheung WC, Simchi-Levi D, Zhu R (2008) Hedging the drift: learning to optimize under non-stationarity. Available at SSRN 3261050

  13. Elzwayie A, El-Shafie A, Mundher YZ, Abdulmohsin AH, Falah AM (2017) RBFNN-based model for heavy metal prediction for different climatic and pollution conditions. Neural Comput Appl 28(8):1991–2003

    Article  Google Scholar 

  14. Enns PK, Masaki T, Kelly N (2014) Time series analysis and spurious regression: An error correction. In Annual Meeting of the Southern Political Science Association, New Orleans, LA

  15. Gil-Alana LA, Payne JE (2017) Time series dynamics of us retail gasoline prices: evidence from fractional integration. Energy Sour, Part B: Econ, Plan, Pol 12(12):1066–1073

    Article  Google Scholar 

  16. Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT press, USA

    MATH  Google Scholar 

  17. Gulli A, Pal S (2017) Deep learning with Keras. Packt Publishing Ltd, UK

    Google Scholar 

  18. 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):3839–3844

    Article  Google Scholar 

  19. Hewamalage H, Bergmeir C, Bandara K (2021) Recurrent neural networks for time series forecasting: current status and future directions. Int J Forecast 37(1):388–427

    Article  Google Scholar 

  20. Hyndman RJ, Athanasopoulos G (2018) Forecasting: Principles and practice. OTexts

  21. Jin X, Yu X, Wang X, Bai Y, Su T, Kong J (2020) Prediction for time series with CNN and LSTM. In Proceedings of the 11th International Conference on Modelling, Identification and Control, pages 631–641. Springer

  22. Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980

  23. Li T, Hua M, Wu X (2020) A hybrid CNN-LSTM model for forecasting particulate matter (pm2. 5). IEEE Access 8:26933–26940

    Article  Google Scholar 

  24. Lim B, Sercan Ö Arık, Loeff N, Pfister T (2021) Temporal fusion transformers for interpretable multi-horizon time series forecasting. International Journal of Forecasting

  25. Liu S, Zhang C, Ma J (2017) CNN-LSTM neural network model for quantitative strategy analysis in stock markets. In International Conference on Neural Information Processing, pages 198–206. Springer

  26. Livieris IE, Iliadis L, Pintelas P (2021) On ensemble techniques of weight-constrained neural networks. Evolv Syst 12(1):155–167

    Article  Google Scholar 

  27. Livieris IE, Kiriakidou N, Stavroyiannis S, Pintelas P (2021) An advanced CNN-LSTM model for cryptocurrency forecasting. Electronics 10(3):287

    Article  Google Scholar 

  28. Livieris IE, Pintelas E, Kiriakidou N, Stavroyiannis S (2020) An advanced deep learning model for short-term forecasting U.S. natural gas price and movement. In IFIP International Conference on Artificial Intelligence Applications and Innovations, pages 165–176. Springer

  29. Livieris IE, Pintelas E, Pintelas P (2020) A CNN-LSTM model for gold price time series forecasting. Neural Computing and Applications

  30. Livieris IE, Stavroyiannis S, Pintelas E, Pintelas P (2020) A novel validation framework to enhance deep learning models in time-series forecasting. Neural Computing and Applications

  31. Wenjie Lu, Jiazheng Li, Jingyang Wang, Lele Qin (2020) A CNN-BiLSTM-AM method for stock price prediction. Neural Computing and Applications, pages 1–13

  32. Luo T, Cao X, Li J, Dong K, Zhang R, Wei X (2021) Multi-task prediction model based on convlstm and encoder-decoder. Intell Data Anal 25(2):359–382

    Article  Google Scholar 

  33. Luong M-T, Pham H, Manning CD (2015) Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025

  34. Mehtab S, Sen J (2020) Stock price prediction using CNN and LSTM-based deep learning models. In 2020 International Conference on Decision Aid Sciences and Application (DASA), pages 447–453. IEEE

  35. Moishin M, Deo RC, Prasad R, Raj N, Abdulla S (2021) Designing deep-based learning flood forecast model with ConvLSTM hybrid algorithm. IEEE Access 9:50982–50993

    Article  Google Scholar 

  36. Montgomery DC, Jennings CL, Kulahci M (2015) Introduction to time series analysis and forecasting. Wiley, Hoboken

    MATH  Google Scholar 

  37. Padilla WR, García J, Molina JM (2021) Improving time series forecasting using information fusion in local agricultural markets. Neurocomputing 452:355–373

    Article  Google Scholar 

  38. Pal A, Prakash PKS (2017) Practical time series analysis: master time series data processing, visualization, and modeling using Python. Packt Publishing Ltd, UK

    Google Scholar 

  39. Panigrahi S, Behera HS (2020) A study on leading machine learning techniques for high order fuzzy time series forecasting. Eng Appl Artif Intell 87:103245

    Article  Google Scholar 

  40. Pedrycz W, Chen S (2013) Time series analysis, modeling and applications. A Computational Intelligence Perspective (e-book Google)

  41. Pengfei X, Houpan Z, Weidong Z (2020) PAD 3-D speech emotion recognition based on feature fusion. In Journal of Physics: Conference Series, 1616: 012106. IOP Publishing

  42. Pérez-Ortiz M, Durán-Rosal AM, Gutiérrez PA, Sánchez-Monedero J, Nikolaou A, Fernández-Navarro F, Hervás-Martínez C (2019) On the use of evolutionary time series analysis for segmenting paleoclimate data. Neurocomputing 326:3–14

    Article  Google Scholar 

  43. Pintelas E, Livieris IE, Stavroyiannis S, Kotsilieris T, Pintelas P (2020)Fundamental research questions and proposals on predicting cryptocurrency prices using DNNs. Technical Report TR20-01, University of Patras

  44. Pintelas E, Livieris IE, Stavroyiannis S, Kotsilieris T, Pintelas P (2020) Investigating the problem of cryptocurrency price prediction - a deep learning approach. In IFIP International Conference on Artificial Intelligence Applications and Innovations, pages 99–110. Springer

  45. Rokach L (2019) Ensemble learning: pattern classification using ensemble methods. World Scientific, Singapore

    Book  MATH  Google Scholar 

  46. Sewak M, Karim MR, Pujari P (2018) Practical convolutional neural networks: implement advanced deep learning models using Python. Packt Publishing Ltd, UK

    Google Scholar 

  47. Sun B, Guo H, Karimi HR, Ge Y, Xiong S (2015) Prediction of stock index futures prices based on fuzzy sets and multivariate fuzzy time series. Neurocomputing 151:1528–1536

    Article  Google Scholar 

  48. Taieb SB, Bontempi G, Atiya AF, Sorjamaa A (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):7067–7083

    Article  Google Scholar 

  49. Ben Taieb S, Hyndman RJ et al (2012) Recursive and direct multi-step forecasting: the best of both worlds, volume 19. Citeseer

  50. Taylor SJ, Letham B (2018) Forecasting at scale. Am Stat 72(1):37–45

    Article  MathSciNet  Google Scholar 

  51. Totaro S, Hussain A, Scardapane S (2020) A non-parametric softmax for improving neural attention in time-series forecasting. Neurocomputing 381:177–185

    Article  Google Scholar 

  52. Wang K, Li K, Zhou L, Yikun H, Cheng Z, Liu J, Chen C (2019) Multiple convolutional neural networks for multivariate time series prediction. Neurocomputing 360:107–119

    Article  Google Scholar 

  53. Wang R, Peng C, Gao J, Gao Z, Jiang H (2020) A dilated convolution network-based LSTM model for multi-step prediction of chaotic time series. Comput Appl Math 39(1):1–22

    Article  MathSciNet  MATH  Google Scholar 

  54. Weigend AS (2018) Time series prediction: forecasting the future and understanding the past. Routledge, UK

    Book  Google Scholar 

  55. Weng L, Sun X, Xia M, Liu J, Yiqing X (2020) Portfolio trading system of digital currencies: a deep reinforcement learning with multidimensional attention gating mechanism. Neurocomputing 402:171–182

    Article  Google Scholar 

  56. Yan K, Wang X, Yang D, Jin N, Huang H, Zhou H (2018) Multi-step short-term power consumption forecasting with a hybrid deep learning strategy. Energies 11(11):3089

    Article  Google Scholar 

  57. Zhang X, Liang X, Zhiyuli A, Zhang S, Xu R, Wu B (2019) AT-LSTM: an attention-based LSTM model for financial time series prediction. In IOP Conference Series: Materials Science and Engineering, volume 569, page 052037. IOP Publishing

  58. Zhou Z-H (2019) Ensemble methods: foundations and algorithms. Chapman and Hall/CRC, UK

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Core Innovation Center, Kallirois 85, GR 11745, Athens, GR, Greece

    Ioannis E. Livieris

  2. Department of Mathematics, University of Patras, 265-00, Patras, GR, Greece

    Panagiotis Pintelas

Authors
  1. Ioannis E. Livieris
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Panagiotis Pintelas
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ioannis E. Livieris.

Ethics declarations

Conflict of interest

The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Livieris, I.E., Pintelas, P. A novel multi-step forecasting strategy for enhancing deep learning models’ performance. Neural Comput & Applic 34, 19453–19470 (2022). https://doi.org/10.1007/s00521-022-07158-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07158-9

Search

Navigation