1. bookVolume 26 (2021): Issue 1 (May 2021)
Journal Details
License
Format
Journal
First Published
08 Nov 2012
Publication timeframe
2 times per year
Languages
English
access type Open Access

Time Series Smoothing Improving Forecasting

Published Online: 04 Jun 2021
Page range: 60 - 70
Journal Details
License
Format
Journal
First Published
08 Nov 2012
Publication timeframe
2 times per year
Languages
English
Abstract

Both statistical and neural network methods may fail in forecasting time series even operating on a great amount of data. It is an open question of which amount fits best to make sufficiently accurate forecasts on it. This implies that the length or time series might be optimised. Hence, the objective is to improve the quality of forecasting by an assumption that parameters are set nearly at their optimal values. To achieve objective, the two types of the benchmark time series are considered: sine-shaped series and random-like series with repeatability. Trend, seasonality, and decay properties embedded into each type. Based on the benchmark of 24 time series models, it is ascertained that, for improving the forecasting, the time series should be smoothed and then downsampled. These operations can be fulfilled successively until the improvement fails. If preliminary smoothing worsens forecasts, the raw time series is straightforwardly downsampled until the forecasting accuracy starts dropping. However, if time series has a visible property of being noised, the preliminary smoothing is strongly recommended.

Keywords

[1] B. Schelter, M. Winterhalder, and J. Timmer, Eds., Handbook of Time Series Analysis: Recent Theoretical Developments and Applications. Wiley, 2006. https://doi.org/10.1002/9783527609970 Search in Google Scholar

[2] V. Kotu and B. Deshpande, “Chapter 10 – Time Series Forecasting,” in Predictive Analytics and Data Mining, V. Kotu, B. Deshpande, Eds. Morgan Kaufmann, 2015, pp. 305–327. https://doi.org/10.1016/B978-0-12-801460-8.00010-0 Search in Google Scholar

[3] J. G. De Gooijer and R. J. Hyndman, “25 Years of Time Series Forecasting,” International Journal of Forecasting, vol. 22, iss. 3, pp. 443–473, 2006. https://doi.org/10.1016/j.ijforecast.2006.01.001 Search in Google Scholar

[4] C. Villasenor, “Chapter 2 – Hyperellipsoidal Neural Network Trained With Extended Kalman Filter for Forecasting of Time Series,” in Artificial Neural Networks for Engineering Applications, A. Y. Alanis, N. Arana-Daniel, C. Lуpez-Franco, Eds. Academic Press, 2019, pp. 9–19. https://doi.org/10.1016/B978-0-12-818247-5.00011-3 Search in Google Scholar

[5] V. Kotu and B. Deshpande, “Chapter 12 – Time Series Forecasting,” in Data Science (Second Edition), V. Kotu, B. Deshpande, Eds. Morgan Kaufmann, 2019, pp. 395–445. https://doi.org/10.1016/B978-0-12-814761-0.00012-5 Search in Google Scholar

[6] M. Fakhfekh and A. Jeribi, “Volatility Dynamics of Crypto-Currencies’ Returns: Evidence from Asymmetric and Long Memory GARCH Models,” Research in International Business and Finance, vol. 51, 101075, 2020. https://doi.org/10.1016/j.ribaf.2019.101075 Search in Google Scholar

[7] F. C. Palm, “Chapter 7 – GARCH Models of Volatility,” in Handbook of Statistics, vol. 14. Elsevier, 1996, pp. 209–240. https://doi.org/10.1016/S0169-7161(96)14009-8 Search in Google Scholar

[8] E. Ghysels, D. R. Osborn, and P. M. M. Rodrigues, “Chapter 13 – Forecasting Seasonal Time Series,” in Handbook of Economic Forecasting, vol. 1, G. Elliott, C. W. J. Granger, A. Timmermann, Eds. Elsevier, 2006, pp. 659–711. https://doi.org/10.1016/S1574-0706(05)01013-X Search in Google Scholar

[9] H. Shimodaira, “Chapter 36 – Time-Series Prediction,” in Expert Systems, C. T. Leondes, Ed. Academic Press, 2002, pp. 1259–1313. https://doi.org/10.1016/B978-012443880-4/50080-6 Search in Google Scholar

[10] R. DiPietro and G. D. Hager, “Chapter 21 – Deep learning: RNNs and LSTM,” in Handbook of Medical Image Computing and Computer Assisted Intervention, S. K. Zhou, D. Rueckert, G. Fichtinger, Eds. Academic Press, 2020, pp. 503–519. https://doi.org/10.1016/B978-0-12-816176-0.00026-0 Search in Google Scholar

[11] T. Masters, “Chapter 4 – Time-Series Prediction,” in Practical Neural Network Recipes in C++, T. Masters, Ed. Morgan Kaufmann, 1993, pp. 47–66. https://doi.org/10.1016/B978-0-08-051433-8.50009-4 Search in Google Scholar

[12] M. Sangiorgio and F. Dercole, “Robustness of LSTM Neural Networks for Multi-Step Forecasting of Chaotic Time Series,” Chaos, Solitons & Fractals, vol. 139, 110045, 2020. https://doi.org/10.1016/j.chaos.2020.110045 Search in Google Scholar

[13] R. Kneusel, Random Numbers and Computers. Springer International Publishing, 2018. https://doi.org/10.1007/978-3-319-77697-2 Search in Google Scholar

[14] B. Quenneville and C. Gagné, “Testing Time Series Data Compatibility for Benchmarking,” International Journal of Forecasting, vol. 29, iss. 4, pp. 754–766, 2013. https://doi.org/10.1016/j.ijforecast.2011.10.001 Search in Google Scholar

[15] A. Stepchenko, J. Chizhov, L. Aleksejeva, and J. Tolujew, “Nonlinear, Non-Stationary and Seasonal Time Series Forecasting Using Different Methods Coupled with Data Preprocessing,” Procedia Computer Science, vol. 104, pp. 578–585, 2017. https://doi.org/10.1016/j.procs.2017.01.175 Search in Google Scholar

[16] P. J. Brockwell and R. A. Davis, Introduction to Time Series and Forecasting. Springer, Cham, 2016. https://doi.org/10.1007/978-3-319-29854-2 Search in Google Scholar

[17] R. E. Edwards, Functional Analysis. Theory and Applications. Hold, Rinehart and Winston, 1965. Search in Google Scholar

[18] A. Jeffrey, “Chapter 27 – Numerical Approximation,” in Handbook of Mathematical Formulas and Integrals, 3rd ed., A. Jeffrey, Ed. Academic Press, 2004, pp. 409–417. https://doi.org/10.1016/B978-012382256-7/50030-0 Search in Google Scholar

[19] W. R. Madych, “Error Estimates for Interpolation by Generalized Splines,” in Curves and Surfaces, P.-J. Laurent, A. Le Méhauté, L. L. Schumaker, Eds. Academic Press, 1991, pp. 297–306. https://doi.org/10.1016/B978-0-12-438660-0.50047-9 Search in Google Scholar

Recommended articles from Trend MD

Plan your remote conference with Sciendo