Perform Time-series Predictions in the R Development Environment by Combining Statistical-based Models with a Decomposition-based Approach

Abstract

The analysis of a time-series (TS) measured or obtained by observing any area is an important step in characterizing a desired system or a phenomenon and predicting its future behavior. More precisely, predicting the value of an unknown variable is the objective of a predictive model used for TS. While doing this, it analyzes the relationships between past data well and reveals future predictions. In this study, the prediction method contrasts the decomposition-based approach with non-decomposition-based approaches. In the comparison process, prediction metrics for assessment, such as RMSE, MAE, MPE, and MAPE were used for method achievements and the results obtained were discussed. The experimental outcomes showed that the proposed decomposition-based approach performs better than non-decomposition-based approach in TS prediction processes.

Keywords

• Decomposition-based prediction
• non-decomposition-based prediction
• time-series
• R language

Perform Time-series Predictions in the R Development Environment by Combining Statistical-based Models with a Decomposition-based Approach

Abstract

Keywords

• Decomposition-based prediiction

References

1. Artasanchez A., Joshi P. Artificial Intelligence with Python, Packt Publishing, Birmingham, UK, 2020.
2. Pala Z., Atici R. Forecasting Sunspot Time Series Using Deep Learning Methods, Solar Physics, 294 (50), 1-14, 2019.
3. Nielsen A. Practical Time Series Analysis Prediction with Statistics and Machine Learning, O’Reilly Media, Inc., Sebastopol, CA, USA, 2020.
4. Pala Z. Using Decomposition-based Approaches to Time Series Forecasting in R Environment, International Conference on Data Science, Machine Learning and Statistics, Van, June 26-29, 2019.
5. Pala Z., Ünlük İ.H., Şahin Ç. Forecasting Low Frequency Electromagnetic Fields Values Time Series Using Python, International Conference on Innovative Engineering Applications (CIEA’ 2018), 20-22 Sep, Sivas, Turkey, 2017.
6. Mills T.C. Applied Time Series Analysis A Practical Guide to Modeling and Forecasting, Academic Press, London, UK, 2019.
7. Hyndman R.J., Athanasopoulos G. Forecasting: Principles and Practice (second ed.), Monash University, Australia, 2018.
8. Cleveland, R. B., Cleveland, W. S., McRae, J. E., & Terpenning, I. J. STL: A seasonal-trend decomposition procedure based on loess. Journal of Official Statistics, 6 (1), 3–33, 1990.

9. Yameogo B. L. M., Charlton D. W., Doucet D., Desrosiers C, O'Sullivan M, Tremblay C. Trends in Optical Span Loss Detected Using the Time Series Decomposition Method, in Journal of Lightwave Technology, 38 (18), 5026-5035, 2020.
10. Namin S.S., Namin A.S. Forecasting economic and financial time series: Arima vs. LSTM, Texas Tech University, TX, USA, 2018.
11. Adhikari R., Agrawal RK. An Introductory Study on Time Series Modeling and Forecasting, arXiv:1302.6613 [cs.LG], LAP Lambert Academic Publishing, Germany, 2013.
12. Hyndman R.J., Khandaka Y. Automatic Time Series Forecasting: The forecast Package for R, Journal of Statistical Software, 27 (3), 1-22, 2008.
13. Alghamdi T., Elgazzar K., Bayoumi M., Sharaf T., Shah S. Forecasting Traffic Congestion Using ARIMA Modeling, 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC), Tangier, Morocco, 1227-1232, 2019.
14. Frank E., Trigg L., Holmes G. et al. Technical Note: Naive Bayes for Regression. Machine Learning 41, 5-25, 2000.