METODE AVERAGE-BASED WEIGHTED FUZZY INTEGRATED TIME SERIES LEE HIGH ORDER (Studi Kasus pada Peramalan Mata Uang Kripto Bitcoin)

• Main Author: Sarmila Nurhasanah, - (Author)
• Format: Book
• Published: 2022-04-20.
• Subjects: Thesis; NonPeerReviewed
• Online Access: Link Metadata
• Notes: http://repository.upi.edu/72351/1/S_MAT_1801164_Title.pdf; http://repository.upi.edu/72351/2/S_MAT_1801164_Chapter1.pdf; http://repository.upi.edu/72351/3/S_MAT_1801164_Chapter2.pdf; http://repository.upi.edu/72351/4/S_MAT_1801164_Chapter3.pdf; http://repository.upi.edu/72351/5/S_MAT_1801164_Chapter4.pdf; http://repository.upi.edu/72351/6/S_MAT_1801164_Chapter5.pdf; http://repository.upi.edu/72351/7/S_MAT_1801164_Appendix.pdf
• Keywords: L Education (General); QA Mathematics

Fuzzy time series (FTS) is one of the data forecasting methods that was first introduced by Song and Chissom in 1993. In its application, the FTS method forecasting uses data in the form of fuzzy sets where the set comes from real numbers over the actual data universe. One of the important aspects in FTS forecasting is determining the exact length of the interval, this is because it will affect the forecasting results. The method in determining the length of the interval is the interval method with an average basis (Average-Based) which will form an appropriate fuzzy relationship and produce good forecasts. In producing better forecasts and weighting, the FTS method has undergone many developments, one of which is the Weighted Fuzzy Integrated Time Series (WFITS) which assigns different weights to each relationship formed. This study discusses the Average-Based WFITS method with the high-order Lee algorithm with the case study used is Bitcoin crypto currency data. Mean Absolute Percentage Error (MAPE) is used to calculate the accuracy of forecasting values. The purpose of this study is to determine the accuracy of the High Order Average-Based WFITS Lee method and the forecasting results of this method on Bitcoin crypto currency data. The data used from August 1, 2021 to April 5, 2022 obtained very good forecasting results with MAPE values of 1.84% for Training data and 1.76% for Testing data.