The Time Series Forecasting Method based on Causal Convolution and RNN

Authors

  • Bo He
  • Qingqing Zhang
  • Dali Tang
  • Kaiwei Zhu

DOI:

https://doi.org/10.54097/cpl.v11i1.10191

Keywords:

Enter Time series forecasting; Deep learning; Convolutional neural nets; Recurrent neural nets; Transformer nets.

Abstract

The analysis of time series in order to discover their intrinsic regularities and to predict future developments is an important academic and applied tool. With the development of sensor and network technology, how to perform accurate and efficient predictive analysis based on large amounts of historical time-series data has become an urgent problem. Time series forecasting has developed rapidly in recent years, with deep learning techniques being used extensively to produce research results. This paper provides an overview of the common characteristics and metrics used to evaluate time series, The traditional methods and machine learning methods involved in time series forecasting are discussed and the applications of deep learning methods, including convolutional neural networks(CNN),recurrent neural networks(RNN) and transformer networks, in time forecasting are highlighted and the advantages and disadvantages of various deep learning based time series methods are compared.

References

CI B C, ZHANG P Y. Financial time series forecast based on ARIMA-LSTM model[J]. Statistics & Decision, 2022, 38 (11): 145-149.

CHE C C, WANG H W, NI X M, et al. Residual life prediction of aeroengine based on 1D-CNN and Bi-LSTM[J]. Journal of Mechanical Engineering, 2021, 57 (14): 304-312.

LUO X M, LI J B, HU P. E-commerce inventory optimization strategy based on time series forecasting[J]. Systems Engineering,2014, 32 (6): 91-98.

SONG Y Q, ZHOU G L, ZHU Y L. Present Status and Challenges of Big Data Processing in Smart Grid[J]. Power System Technology, 2013, 37 (04): 927-935.

Wen Q, He K, Sun L, et al. RobustPeriod: Robust time-frequency mining for multiple periodicity detection[C]. Proceedings of the 2021 International Conference on Management of Data, 2021: 2328-2337.

LI P P, SONG S X, WANG J M. Time Series Symmetric Pattern Mining[J]. Journal of Software, 2022, 33 (3): 968− 984.

Willmott C J, Matsuura K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance[J]. Climate research, 2005, 30 (1): 79-82.

Wang Z, Bovik A C. Mean squared error: Love it or leave it ? A new look at signal fidelity measures[J]. IEEE signal processing magazine, 2009, 26 (1): 98-117.

Chai T, Draxler R R. Root mean square error (RMSE) or mean absolute error (MAE) -Arguments against avoiding RMSE in the literature[J]. Geoscientific model development, 2014, 7 (3): 1247-1250.

De Myttenaere A, Golden B, Le Grand B, et al. Mean absolute percentage error for regression models[J]. Neurocomputing, 2016, 192: 38-48.

Cameron A C, Windmeijer F A G. An R-squared measure of goodness of fit for some common nonlinear regression models[J]. Journal of econometrics, 1997, 77 (2): 329-342.

LI S X, LI B G. Comparison of prediction method based on SARIMA model and X-12-ARIMA seasonal adjustment method[J]. Statistics & Decision, 2018, 34 (18): 39-42.

CHEN R, LIANG C Y, XIE F W. Application of nonlinear time series forecasting methods based on support vector regression[J]. Journal of Hefei University of Technology (Natural Science), 2013, 36 (3): 369-374.

ELSAYED S, THYSSENS D, RASHED A, et al. Do we really need deep learning models for time series forecasting? [Z]. arXiv: 2101. 02118, 2021.

M. Das, S.K. Ghosh. semBnet: A semantic bayesian network for multivariate prediction of meteorological time series data[J]. PatternRecognition Letter, 2017, 93 (1): 192-201.

Borovykh A, Bohte S, Oosterlee C W. Conditional time series forecasting with convolutional neural networks[J]. arXiv preprint, arXiv: 1703. 04691, 2017.

Bai S, Kolter J Z, Koltun V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[J]. arXiv preprint, arXiv: 1803. 01271, 2018.

LIU M H, ZENG A L, CHEN M X, et al. SCINet: Timeseries modeling and Forecasting with sample convolution and interaction[Z]. arXiv: 2106. 09305, 2021.

Schuster M, Paliwal K K. Bidirectional recurrent neural networks[J]. IEEE transactions on Signal Processing, 1997, 45 (11): 2673-2681.

Graves A, Schmidhuber J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J]. Neural networks, 2005, 18(5-6): 602-610.

Qi Y, Li C, Deng H, et al. A deep neural framework for sales forecasting in e-commerce[C], Proceedings of the 28th ACM International Conference on Information and Knowledge Management, Beijing, Nov 3-7, 2019. New York: ACM, 2019: 299-308.

Xin S, Ester M, Bu J, et al. Multi-task based sales predictions for online promotions[C], Proceedings of the 28th ACM International Conference on Information and Knowledge Management, Beijing, Nov 3-7, 2019. New York: ACM, 2019: 2823-2831.

VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C], Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, CA, USA: Curran Associates Inc. 2017: 6000-6010.

Wu S, Xiao X, Ding Q, et al. Adversarial sparse transformer for time series forecasting[J]. Advances in neural information processing systems, 2020, 33: 17105- 17115.

Zhou H, Zhang S, Peng J, et al. Informer: Beyond efficient transformer for long sequence time-series forecasting[C], Proceedings of the AAAI Conference on Artificial Intelligence, virtual, Feb 2-9, 2021. California: AAAI,2021, 35 (12): 11106-11115.

Lim B, Arı k S Ö, Loeff N, et al. Temporal fusion transformers for interpretable multi-horizon time series forecasting[J]. International Journal of Forecasting, 2021, 37 (4): 1748-1764.

Lin Y, Koprinska I, Rana M. SSDNet: State space decomposition neural network for time series forecasting[C], 2021 IEEE International Conference on Data Mining (ICDM), Auckland, Dec 7-10, 2021. IEEE, 2021: 370-378.

Wu H, Xu J, Wang J, et al. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting[J]. Advances in Neural Information Processing Systems, 2021, 34: 22419-22430.

Qi X, Hou K, Liu T, et al. From known to unknown:Knowledge-guided transformer for time-series sales forecasting in Alibaba[J]. arXiv preprint, arXiv: 2109. 08381, 2021.

Zhou T, Ma Z, Wen Q, et al. FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting[J]. arXiv preprint, arXiv: 2201. 12740, 2022.

Wen Q, Gao J, Song X, et al. RobustSTL: A robust seasonal-trend decomposition algorithm for long time series[C], Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, Jan 27-Feb 1, 2019. California: AAAI, 2019, 33(01): 5409-5416.

Li Y, Lu X, Xiong H, et al. Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution[J]. arXiv preprint, arXiv:2301.02068, 2023.

WAN C, LI W Z, DING W X, et al. A Multivariate Time Series Forecasting Algorithm Based on Self-Evolutionary Pre-training[J]. Chinese Journal of Computer, 2022, 45(03):513-525.

SALINAS D, FLUNKERT V, GASTHAUS J, et al. DeepAR: probabilistic forecasting with autoregressive recurrent networks[J]. International Journal of Forecasting, 2020, 36 (3): 1181-1191.

Downloads

Published

14-07-2023

Issue

Section

Articles

How to Cite

He , B., Zhang, Q., Tang, D., & Zhu, K. (2023). The Time Series Forecasting Method based on Causal Convolution and RNN. Computer Life, 11(1), 19-24. https://doi.org/10.54097/cpl.v11i1.10191