Comparative Analysis of Neural Networking and Regression Models for Time Series Forecasting
https://doi.org/10.38086/2522-9613-2019-2-60-68
Abstract
Applicability of neural nets in time series forecasting has been considered and researched. For this, training of neural network on various time series with preliminary selection of optimal hyperparameters has been performed. Comparative analysis of received neural networking forecasting model with linear regression has been performed. Conditions, affecting on accuracy and stability of results of the neural network, have been revealed.
About the Author
S. V. Sholtanyuk
Belarusian State University
Belarus
Belarus
Assistant of the Department of Computer Applications and Systems, FAMCS
4 Independence Ave., 220030 Minsk, Republic of Belarus
References
1. Chuchueva I. A. Model' prognozirovaniya vremennykh ryadov po vyborke maksimal'nogo pravdopodobiya [The time series forecast model based on maximum likeness set] Candidate of science dissertation. M.: Bauman Moscow State Technical University, 2012. 155 p. (In Russian).
2. Hornik K., Stinchcombe M., White H. Multilayer feedforward networks are universal approximators, Neural Networks 2 (5) (1989). pp. 359-366.
3. Bengio Y., LeCun Y. Scaling learning algorithms towards AI. In L. Bottou et al. (Eds.), Large-Scale Kernel Machines. Cambridge, MA, MIT Press, 2007. pp. 323-362.
4. R Core Team (2018). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. Available at: https://www.R-project.org/ (accessed: 19.01.2019)
5. JJ Allaire and Francois Chollet (2018). keras: R Interface to 'Keras'. R package version 2.2.0. Available at: https:// CRAN.R-project.org/package=keras. (accessed: 19.01.2019)
6. J. Duchi. E. Hazan. Y. Singer. Adaptive Subgradient Methods for Online Learning and Stochastic Optimization, Journal of Machine Learning Research, 12 (2011). pp. 2121-2159.
7. Ruder S. An overview of gradient descent optimisation algorithms. arXiv preprint arXiv:1609.04747v2. Available at: https://arxiv.org/abs/1609.04747. (accessed: 19.01.2019)
Review
For citations:
Sholtanyuk S.V. Comparative Analysis of Neural Networking and Regression Models for Time Series Forecasting. Digital Transformation. 2019;(2):60-68. (In Russ.) https://doi.org/10.38086/2522-9613-2019-2-60-68
Views: 4944
Email this article 