Time series forecasting methods from traditional approaches to deep learning: Python and MATLAB applications

Öz

Time series analysis has been a crucial topic in various scientific fields for many years due to its importance in predicting future observations. The forecasting of time-dependent data has been approached using both traditional and modern methods. In recent years, deep learning, one of the most advanced artificial intelligence techniques, has emerged as a powerful tool for time series analysis. In this context, this study examines the evolution of time series forecasting methods from past to present, providing a comprehensive comparison of their advantages and disadvantages. Furthermore, real-time applications are demonstrated using MATLAB and Python, offering a practical implementation of these methodologies.

Anahtar Kelimeler

• Time series analysis
• Box-Jenkins
• Artificial neural networks
• Deep learning
• MATLAB
• Python

Geleneksel yaklaşımlardan derin öğrenmeye zaman serisi öngörü yöntemleri: Pyhton ve MATLAB uygulamaları

Öz

Zaman serisi analizi birçok bilimsel alanda ihtiyaç duyulan bir araştırma alanı olarak uzun yıllardır önemini korumaktadır. Belirli bir zaman noktasındaki değişkenlerin davranışlarını anlama, modelleme ve geleceğe ilişkin öngörülerde bulunma taşıyan zaman serisi analizi geleneksel ve modern yöntemlerle gerçekleştirilmektedir. Son yıllarda büyük bir atılım ile gelişen yapay zekâ yöntemlerinin en güçlülerinden olan derin öğrenme, zaman serisi analizi için oldukça güçlü bir yaklaşım olarak kabul edilmektedir. Bu amaç doğrultusunda bu çalışmada zaman serisi analizi için kullanılan yöntemlerin geçmişten günümüze gelişimini ve birbirine olan avantaj ve dezavantajlarıyla detaylı bir şekilde incelenerek MATLAB ve Python kodlarıyla gerçek zamanlı kullanımı sunulmaktadır.

Anahtar Kelimeler

• Zaman serisi analizi
• Box-Jenkins
• Yapay sinir ağları
• Derin ağlar
• MATLAB
• Python

Kaynakça

1. [1] Akaike, H. (1974) A New Look at the Statistical Model Identification, IEEE Transactions On Automatic Control, 19: 716–723.
2. [2] Mcculloch, W.S. and Pitts, W.H. (1943) A logical calculus of the ideas immanent in nervous activity, Bulletin of Mathematical Biophysics, 5: 115 – 133.
3. [3] Werbos, P.J. (1974) Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences, PhD thesis, Harvard University.
4. [4] Rumelhart, D.E., Hinton, G.E. ve Williams, R.J. (1986) Learning representations by back-propagating errors, Nature, 323: 533–536.
5. [5] Box, G.E.P., Jenkins, G.M., ve Reinsel, G.C. (1976) Time Series Analysis, Forecasting and Control. Third Edition. Holden-Day, 712s.
6. [6] Shumway, R. H., Stoffer, D. S., & Stoffer, D. S. (2000). Time series analysis and its applications (Vol. 3, p. 4). New York: Springer.
7. [7] Australian Bureau of Statistics. (1992). Consumer Price Index, 1972–1991 [Data set]. ABS Catalogue No. 6401.0. https://www.abs.gov.au/statistics.
8. [8] Aladag, C. H., Egrioglu, E., Gunay, S., & Basaran, M. A. (2010). Improving weighted information criterion by using optimization. Journal of computational and applied mathematics, 233(10), 2683-2687.

9. [9] Günay, S., Eğrioğlu, E., Ç.H.Aladağ (2007) Tek Değişkenli Zaman Serileri Analizine Giriş, Hacettepe Üniversitesi Yayınları, Ankara, 230s.
10. [10] Rosenblatt, F. (1958) The Perceptron: A Probabilistic Model For Information Storage And Organization In The Brain, Psychological Review, 65: 386 – 408.
11. [11] Minsky, M., Papert, S. (1969). Perceptrons: An Introduction to Computational Geometry. Cambridge, MA, USA: MIT Press.
12. [12] Bal, C., & Demir, S. (2017). Forecasting TRY/USD exchange rate with various artificial Neural Network Models. TEM Journal, 6(1), 11.
13. [13] Egrioglu, E., Yolcu, U., Aladag, C. H., & Bas, E. (2015). Recurrent multiplicative neuron model artificial neural network for non-linear time series forecasting. Neural Processing Letters, 41, 249-258.
14. [14] LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. nature, 521(7553), 436-444.
15. [15] Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
16. [16] LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989). Backpropagation applied to handwritten zip code recognition. Neural computation, 1(4), 541-551.
17. [17] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25.
18. [18] Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., ... & Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1-9).
19. [19] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
20. [20] Kiranyaz, S., Avci, O., Abdeljaber, O., Ince, T., Gabbouj, M., & Inman, D. J. (2021). 1D convolutional neural networks and applications: A survey. Mechanical systems and signal processing, 151, 107398.