Comparing the Accuracy of Classical and Machine Learning Methods in Time Series Forecasting: A Case Study of USA Inflation
AbstractThis paper presents a comparison of statistical classical methods and machine learning algorithms for time series forecasting notably the Exponential Smoothing, hybrid ARIMA-GARCH model, K-Nearest Neighbors (KNN), Prophet, and Long-Short Term Memory (LSTM). The data set used in this study is related to US inflation and covers the period from 1965 to 2021. The performance of the models was evaluated using different metrics especially Mean Squared Error (MSE), Mean Absolute Error (MAE), Median Absolute Error (Median AE), and Root Mean Squared Error (RMSE). The results of the numerical comparison show that the best performance was achieved by Exponential Smoothing, followed closely by KNN. The results indicate that these two models are well-suited for forecasting inflation in the US. ARIMA-GARCH, LSTM, and Prophet performed relatively poorly in comparison. Overall, the findings of this study can be useful for practitioners in choosing the most suitable method for forecasting inflation in the US in the short-term period.
Achmad Muchayan (2019). Comparison of Holt and Brown’s Double Exponential Smoothing Methods in The Forecast of Moving Price for Mutual Funds. Journal of Applied Science, Engineering, Technology, and Education Vol. 1 No. 2.
Board of Governors of the Federal Reserve System. (2021). Inflation Data. Retrieved from https://fred.stlouisfed.org/
Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. Journal of Econometrics, 31, 307–327.
Cheng Yang and Shuhua Guo (2021). Inflation Prediction Method Based on Deep Learning, Computational Intelligence and Neuroscience, vol. 2021, Article ID 1071145, 6 pages.
Friedman, M. (1996). The Counter-Revolution in Monetary Theory. In: Wood, G.E. (eds) Explorations in Economic Liberalism. Palgrave Macmillan, London.
Goodman, L. S. (1965). Book Review: Smoothing, Forecasting, and Prediction of Discrete Time Series. Journal of Marketing Research, 2(3), 314–315.
Ionut-Cristian Baciu (2015). Stochastic models for forecasting inflation rate. Empirical evidence from Romania, 7th International Conference on Globalization and Higher Education in Economics and Business Administration, GEBA 2013.
Jose F. Torres, et al. (2021). ´ Deep Learning for Time Series Forecasting: A Survey. Big Data.3-2.3-21
J. Youness and M. Driss (2022). An ARIMA Model for Modeling and Forecasting the Dynamic of Univariate Time Series: The case of Moroccan Inflation Rate, International Conference on Intelligent Systems and Computer Vision (ISCV), Fez, Morocco, 2022, pp.1-5.
J. Youness and M. Driss, (2022). LSTM Deep Learning vs ARIMA Algorithms for Univariate Time Series Forecasting: A case study, 2022 8th International Conference on Optimization and Applications (ICOA), Genoa, Italy, pp. 1-4.
Jouilil Y and Mentagui D. (2023). Comparing The Forecasting Accuracy Metrics Of Support Vector Regression And ARIMA Algorithms For Non-Stationary Time Proces. Mathematics and Statistics.
Livia Paranhos (2022). Predicting Inflation with Recurrent Neural Networks. R&R at the International Journal of Forecasting.
Mankiw, N. G. (2016). Principles of microeconomics (8th ed.). CENGAGE Learning Custom Publishing.
Rob J. Hyndman and Anne B. Koehler, (2006). Another look at measures of forecast accuracy, International Journal of Forecasting, Volume 22, Issue 4, Pages 679-688.
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).