Article

PLAE: Time-Series Prediction Improvement by Adaptive Decomposition

Authors:

Wei ZhengAuthors Info & Claims

PRICAI 2022: Trends in Artificial Intelligence: 19th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2022, Shanghai, China, November 10–13, 2022, Proceedings, Part I

Pages 394 - 407

https://doi.org/10.1007/978-3-031-20862-1_29

Published: 10 November 2022 Publication History

Abstract

Univariate time-series forecasting is a kind of commonly encountered yet tough problem. Most of the forecast algorithms’ performance is constrained by the limited information due to the single input dimension. No matter how capable a forecast algorithm is, an accurate output cannot be rendered on an unpredictable time-series. This paper presents PLAE (Predictability Leveraging Auto-Encoder), a Seq2Seq model for univariate time-series data aiming to enhance the accuracy of the given algorithm without dimensional adaptation. The main idea is decomposing the original input data into a group of more predictable microscopic time-series on which the forecast algorithm can deliver a more accurate output. And the final prediction is rendered by aggregating those components back to the original one-dimension. Experiments on three public data sets and one real-world data set show that PLAE can improve the forecast accuracy for 23.38% in terms of MAPE and 19.76% in terms of RMSE. Besides, experimental evidence shows that PLAE’s adaptive non-linear decomposition mechanism outperforms the pre-defined additive decomposition w.r.t. both forecasting performance and components’ interpretability.

References

[1]

Bandt C and Pompe B Permutation entropy: a natural complexity measure for time series Phys. Rev. Lett. 2002 88 17

[2]

Bao W, Yue J, and Rao Y A deep learning framework for financial time series using stacked autoencoders and long-short term memory PloS One 2017 12 7

[3]

Borovykh, A., Bohte, S., Oosterlee, C.W.: Conditional time series forecasting with convolutional neural networks. arXiv preprint arXiv:1703.04691 (2017)

[4]

Box GE, Jenkins GM, Reinsel GC, and Ljung GM Time Series Analysis: Forecasting and Control 2015 Hoboken Wiley

[5]

Chatfield C The holt-winters forecasting procedure J. Roy. Stat. Soc. Ser. C (Appl. Stat.) 1978 27 3 264-279

[6]

Chen KY and Wang CH A hybrid SARIMA and support vector machines in forecasting the production values of the machinery industry in Taiwan Expert Syst. Appl. 2007 32 1 254-264

[7]

Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794 (2016)

[8]

Chen Y, Kang Y, Chen Y, and Wang Z Probabilistic forecasting with temporal convolutional neural network Neurocomputing 2020 399 491-501

[9]

Cleveland RB, Cleveland WS, McRae JE, and Terpenning I STL: a seasonal-trend decomposition J. Off. Stat 1990 6 1 3-73

[10]

Du, S., Li, T., Horng, S.J.: Time series forecasting using sequence-to-sequence deep learning framework. In: 2018 9th International Symposium on Parallel Architectures, Algorithms and Programming (PAAP), pp. 171–176. IEEE (2018)

[11]

Esling P and Agon C Time-series data mining ACM Comput. Surv. (CSUR) 2012 45 1 1-34

[12]

Ester, M., Kriegel, H.P., Sander, J., Xu, X., et al.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: KDD, vol. 96, pp. 226–231 (1996)

[13]

Gardner ES Jr Exponential smoothing: the state of the art J. Forecast. 1985 4 1 1-28

[14]

Garland J, James R, and Bradley E Model-free quantification of time-series predictability Phys. Rev. E 2014 90 5

[15]

Huang, N.E., et al.: The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. Roy. Soc. Lond. Ser. A Math. Phys. Eng. Sci. 454(1971), 903–995 (1998)

[16]

Ke, G., et al.: LightGBM: a highly efficient gradient boosting decision tree. In: Advances in Neural Information Processing Systems 30, pp. 3146–3154 (2017)

[17]

Kontoyiannis I, Algoet PH, Suhov YM, and Wyner AJ Nonparametric entropy estimation for stationary processes and random fields, with applications to English text IEEE Trans. Inf. Theory 1998 44 3 1319-1327

[18]

Kumar U and De Ridder K GARCH modelling in association with FFT-ARIMA to forecast ozone episodes Atmos. Environ. 2010 44 34 4252-4265

[19]

Li, S., et al.: Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting. In: Advances in Neural Information Processing Systems 32, pp. 5243–5253 (2019)

[20]

Liao M, Lyu P, He M, Yao C, and Bai X Mask TextSpotter: an end-to-end trainable neural network for spotting text with arbitrary shapes IEEE Trans. Pattern Anal. Mach. Intell. 2019 43 2 532-548

[21]

McLeod AI and Li WK Diagnostic checking ARMA time series models using squared-residual autocorrelations J. Time Ser. Anal. 1983 4 4 269-273

[22]

Molgedey L and Ebeling W Local order, entropy and predictability of financial time series Eur. Phys. J. B Condens. Matter Complex Syst. 2000 15 4 733-737

[23]

Navet N and Chen SH Brabazon A and O’Neill M On predictability and profitability: would GP induced trading rules be sensitive to the observed entropy of time series? Natural Computing in Computational Finance 2008 Heidelberg Springer 197-210

[24]

Pennekamp F et al. The intrinsic predictability of ecological time series and its potential to guide forecasting Ecol. Monogr. 2019 89 2

[25]

Salinas D, Flunkert V, Gasthaus J, and Januschowski T DeepAR: probabilistic forecasting with autoregressive recurrent networks Int. J. Forecast. 2020 36 3 1181-1191

[26]

Song C, Qu Z, Blumm N, and Barabási AL Limits of predictability in human mobility Science 2010 327 5968 1018-1021

[27]

Tang, Z., De Almeida, C., Fishwick, P.A.: Time series forecasting using neural networks vs. Box-Jenkins methodology. Simulation 57(5), 303–310 (1991)

[28]

Taylor SJ and Letham B Forecasting at scale Am. Stat. 2018 72 1 37-45

[29]

Teunter RH, Syntetos AA, and Babai MZ Intermittent demand: linking forecasting to inventory obsolescence Eur. J. Oper. Res. 2011 214 3 606-615

[30]

Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)

[31]

Wen M, Li P, Zhang L, and Chen Y Stock market trend prediction using high-order information of time series IEEE Access 2019 7 28299-28308

[32]

Xu P, Yin L, Yue Z, and Zhou T On predictability of time series Phys. A Stat. Mech. Appl. 2019 523 345-351

[33]

Yu, H.F., Rao, N., Dhillon, I.S.: Temporal regularized matrix factorization for high-dimensional time series prediction. In: Advances in Neural Information Processing Systems 29 (2016)

[34]

Zhou, H., et al.: Informer: beyond efficient transformer for long sequence time-series forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 11106–11115 (2021)

[35]

Zhu, Z., et al.: MixSeq: connecting macroscopic time series forecasting with microscopic time series data. In: Advances in Neural Information Processing Systems 34 (2021)

Cited By

Deng JDeng JJiang RSong XElkind E(2023)Learning Gaussian mixture representations for tensor time series forecastingProceedings of the Thirty-Second International Joint Conference on Artificial Intelligence10.24963/ijcai.2023/231(2077-2085)Online publication date: 19-Aug-2023
https://dl.acm.org/doi/10.24963/ijcai.2023/231

Index Terms

PLAE: Time-Series Prediction Improvement by Adaptive Decomposition

Index terms have been assigned to the content through auto-classification.

Recommendations

Recursive Bayesian echo state network with an adaptive inflation factor for temperature prediction

Temperature prediction is a challenging problem and a concern in energy, environment, industry and agriculture etc. Climate models and statistical time-series forecasting methods are the ineffective forecasting tools of the long-range temperature ...
Comparison of Predictive Models for Forecasting Time-series Data
ICBDR '19: Proceedings of the 3rd International Conference on Big Data Research

Dramatic increase in data size enabled researchers to study analysis and prediction of big data. Big data can be formed in many ways and one alternative is through the use of sensors. An important aspect of data coming from sensors is that they are time-...
A hybrid evolutionary decomposition system for time series forecasting

In the field of time series forecasting, the combination of linear and nonlinear models has been explored to improve the accuracy of predictions when compared with the performance of individual models. Traditional forecasting methods such as the ...

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

PRICAI 2022: Trends in Artificial Intelligence: 19th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2022, Shanghai, China, November 10–13, 2022, Proceedings, Part I

Nov 2022

615 pages

ISBN:978-3-031-20861-4

DOI:10.1007/978-3-031-20862-1

Editors:
Sankalp Khanna
CSIRO Australian e-Health Research Centre, Brisbane, QLD, Australia
,
Jian Cao
Shanghai Jiao Tong University, Shanghai, China
,
Quan Bai
University of Tasmania, Hobart, TAS, Australia
,
Guandong Xu
University of Technology Sydney, Sydney, NSW, Australia

© The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 10 November 2022

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 01 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Deng JDeng JJiang RSong XElkind E(2023)Learning Gaussian mixture representations for tensor time series forecastingProceedings of the Thirty-Second International Joint Conference on Artificial Intelligence10.24963/ijcai.2023/231(2077-2085)Online publication date: 19-Aug-2023
https://dl.acm.org/doi/10.24963/ijcai.2023/231

View Options

View options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents