Exploration of machine learning forecasting methods in M4 competition / Muhammad Halim Hamdan and Shuzlina Abdul-Rahman

• Main Authors: Hamdan, Muhammad Halim (Author), Abdul-Rahman, Shuzlina (Author)
• Format: Book
• Published: Universiti Teknologi MARA, Perak, 2021-05.
• Subjects: Article; PeerReviewed
• Online Access: Link Metadata
• Notes: https://ir.uitm.edu.my/id/eprint/61456/1/61456.pdf; Exploration of machine learning forecasting methods in M4 competition / Muhammad Halim Hamdan and Shuzlina Abdul-Rahman. (2021) Mathematical Sciences and Informatics Journal (MIJ) <https://ir.uitm.edu.my/view/publication/Mathematical_Sciences_and_Informatics_Journal_=28MIJ=29/>, 2 (1). pp. 21-30. ISSN 2735-0703
• Keywords: QA Mathematics; Analysis; Analytical methods used in the solution of physical problems

There are so many forecasting algorithms and techniques available. The abilities of Data Mining to obtain and gather data from multiple sources is very useful to researcher, practitioner, business and more. From a long list of forecasting algorithms that have been built throughout the years, it will be exhaustive for someone to go through the list one by one to choose which algorithm to use. With M competition established, there are many more new techniques being innovated each time it is organized. This research aims to compare and contrast the machine learning forecasting techniques that are used in M4 Competition, to get better understanding on each technique and to identify the best technique. Three machine learning techniques from M4 Competition were chosen to be compared in this research. Each technique was replicated, trained and tested accordingly. M4 competition dataset was used in this research, with 100,000 time series data and multiple data frequency, which is enough to replicate the real-world situation. The results indicate that the three techniques have their strength, with RNN+ES technique on top of it. RNN+ES and CNN-TS performed well in relative to Naive2 benchmark, while k-NS model performed the worst. Further research on the datasets and investigation of each model to further improve its capabilities are needed to improve the performance of the model.