Traditional vs Machine Learning Approaches: A Comparison of Time Series Modeling Methods

Authors

Miguel E. Bonilla Jr., Southern Methodist UniversityFollow
Jason McDonald, Southern Methodist UniversityFollow
Tamas Toth, Southern Methodist UniversityFollow
Bivin Sadler, Southern Methodist UniversityFollow

Abstract

In recent years, various new Machine Learning and Deep Learning algorithms have been introduced, claiming to offer better performance than traditional statistical approaches when forecasting time series. Studies seeking evidence to support the usage of ML/DL over statistical approaches have been limited to comparing the forecasting performance of univariate, linear time series data. This research compares the performance of traditional statistical-based and ML/DL methods for forecasting multivariate and nonlinear time series.

Recommended Citation

Bonilla, Miguel E. Jr.; McDonald, Jason; Toth, Tamas; and Sadler, Bivin (2023) "Traditional vs Machine Learning Approaches: A Comparison of Time Series Modeling Methods," SMU Data Science Review: Vol. 7: No. 2, Article 2.
Available at: https://scholar.smu.edu/datasciencereview/vol7/iss2/2

Creative Commons License

This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License