Abstract
Machine Learning (ML) methods have been proposed in the academic literature as alternatives to statistical ones for time series forecasting. Yet, scant evidence is available about their relative performance in terms of accuracy and computational requirements. The purpose of this paper is to evaluate such performance across multiple forecasting horizons using a large subset of 1045 monthly time series used in the M3 Competition. After comparing the post-sample accuracy of popular ML methods with that of eight traditional statistical ones, we found that the former are dominated across both accuracy measures used and for all forecasting horizons examined. Moreover, we observed that their computational requirements are considerably greater than those of statistical methods. The paper discusses the results, explains why the accuracy of ML models is below that of statistical ones and proposes some possible ways forward. The empirical results found in our research stress the need for objective and unbiased ways to test the performance of forecasting methods that can be achieved through sizable and open competitions allowing meaningful comparisons and definite conclusions.
Highlights
Artificial Intelligence (AI) has gained considerable prominence over the last decade fueled by a number of high profile applications in Autonomous Vehicles (AV), intelligent robots, image and speech recognition, automatic translations, medical and law usage as well as beating champions in games like chess, Jeopardy, GO and poker [1]
Until a later time when more advanced Machine Learning (ML) methods become available and in order to simplify things, we suggest that the data is deseasonalized before some ML model is utilized, as research [11] has shown little to no differences between the post-sample accuracy of models applied to original and seasonally adjusted data
A major innovation that has distinguished forecasting from other fields has been the good number of empirical studies aimed at both the academic community as well as the practitioners interested in utilizing the most accurate methods for their various applications and reducing cost or maximizing benefits by doing so
Summary
Artificial Intelligence (AI) has gained considerable prominence over the last decade fueled by a number of high profile applications in Autonomous Vehicles (AV), intelligent robots, image and speech recognition, automatic translations, medical and law usage as well as beating champions in games like chess, Jeopardy, GO and poker [1]. The successes of AI are based on the utilization of algorithms capable of learning by trial and error and improving their performance over time, not just by step-by-step coding instructions based on logic, if- rules and decision trees, which is the sphere of traditional programming. In light of the above, AI found applications in the field of forecasting and a considerable amount of research has been conducted on how a special class of it, utilizing Machine Learning methods (ML) and especially Neural Networks (NNs), can be exploited to improve time series predictions.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
