| Issue |
E3S Web Conf.
Volume 483, 2024
The 3rd International Seminar of Science and Technology (ISST 2023)
|
|
|---|---|---|
| Article Number | 03001 | |
| Number of page(s) | 16 | |
| Section | Trends in Mathematics and Computer Science for Sustainable Living | |
| DOI | https://doi.org/10.1051/e3sconf/202448303001 | |
| Published online | 31 January 2024 | |
Application of Cheng’s Fuzzy Time Series in World Crude Oil Price Prediction
Universitas Terbuka, Information System Department, 15437 South Tangerang, Banten, Indonesia
* Corresponding author: lintang@ecampus.ut.ac.id
Fuzzy time series is a new concept that can be used to predict an event using historical data. Historical data is processed using the principles and logic of fuzzy sets. The aim of this study is to predict world oil prices. The historical data used was from 3 January 2022 to 30 June 2023. This article discusses Cheng’s Fuzzy Time Series application. Determining the number of fuzzy class intervals uses 3 approaches, namely using the Sturges formula, Average-based and Partial Frequency Density. The 3 approaches used will be compared. Fuzzy Time Series with the Sturges formula produces a MAPE of 10.54% and a MSE of 9.13. Average-based Fuzzy Time Series produces a MAPE of 7.64% and a MSE of 5.15. Partial Frequency Density Fuzzy Time Series produces a MAPE of 8.09% and a MSE of 5.99. The results of this study state that Cheng’s Average based Fuzzy Time Series has the best accuracy in predicting world oil prices.
© The Authors, published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.