Framework for Comparing Accuracy of Time-Series Forecasting Methods

The research and development of time-series forecasting requires a relative assessment of forecast accuracy, although determining which model or method to select is difficult. This study creates a simple experimental framework for selecting time-series forecasting methods, based on the methods emplo...

Full description

Saved in:
Bibliographic Details
Published in2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI) pp. 669 - 672
Main Authors Sekitani, Junichi, Murakami, Harumi
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2022
Subjects
Benchmark testing
benchmarking methods
Boosting
Data models
Forecasting
forecasting competitions
Frequency-domain analysis
Informatics
machine learning
Predictive models
time-series methods
Online AccessGet full text

Cover

More Information
Summary:The research and development of time-series forecasting requires a relative assessment of forecast accuracy, although determining which model or method to select is difficult. This study creates a simple experimental framework for selecting time-series forecasting methods, based on the methods employed as benchmarks in theM4 Competition and commonly used in machine learning competitions. We added gradient boosting and other methods used in this study. Our experimental results using M4 data confirmed the high accuracy of the combination and statistical models as in theM4 Competition.
DOI:10.1109/IIAIAAI55812.2022.00136