PERBANDINGAN METODE MARKOV WEIGHTED FUZZY TIME SERIES DENGAN PARTICLE SWARM OPTIMIZATION DAN CAT AND MOUSE BASED OPTIMIZER PADA PERAMALAN HARGA ETHEREUM

ILHAM HARGO SUJANTO, . (2026) PERBANDINGAN METODE MARKOV WEIGHTED FUZZY TIME SERIES DENGAN PARTICLE SWARM OPTIMIZATION DAN CAT AND MOUSE BASED OPTIMIZER PADA PERAMALAN HARGA ETHEREUM. Sarjana thesis, UNIVERSITAS NEGERI JAKARTA.

	Text COVER.pdf Download (2MB)
	Text BAB 1.pdf Download (515kB)
	Text BAB 2.pdf Restricted to Registered users only Download (814kB) | Request a copy
	Text BAB 3.pdf Restricted to Registered users only Download (1MB) | Request a copy
	Text BAB 4.pdf Restricted to Registered users only Download (1MB) | Request a copy
	Text BAB 5.pdf Restricted to Registered users only Download (526kB) | Request a copy
	Text Daftar Pustaka.pdf Download (504kB)
	Text Lampiran.pdf Restricted to Registered users only Download (4MB) | Request a copy

Abstract

Markov Weighted Fuzzy Time Series (MWFTS) merupakan metode peramalan yang menggabungkan konsep deret waktu fuzzy dengan model Markov. Penelitian ini bertujuan membandingkan kinerja MWFTS yang dioptimalkan menggunakan Particle Swarm Optimization (PSO) dan Cat and Mouse Based Optimizer (CMBO) dalam memprediksi harga Ethereum. Kedua algoritma optimasi diterapkan untuk mengoptimalkan batas interval pada MWFTS. Data yang digunakan merupakan data sekunder berupa harga penutupan harian Ethereum periode 1 Januari 2025 hingga 31 Maret 2026 yang diperoleh dari id.investing.com. Dalam penelitian ini, data dibagi menjadi data latih dan data uji dengan perbandingan 8:2, di mana seluruh proses optimasi dilakukan menggunakan data latih, sedangkan data uji digunakan untuk mengevaluasi akurasi prediksi model. Hasil penelitian menunjukkan bahwa penerapan PSO dan CMBO memberikan hasil yang lebih baik dibandingkan MWFTS tanpa optimasi. Berdasarkan hasil perbandingan, optimasi MWFTS-CMBO memperoleh nilai MAE (172,02), MAPE (7,58%), dan RMSE (207,66) yang lebih baik dibandingkan dengan optimasi MWFTS-PSO, yang memiliki nilai MAE (191,47), MAPE (8,57%), dan RMSE (226,46). Hasil ini menunjukkan bahwa metode MWFTS-CMBO memberikan hasil prediksi yang lebih akurat dibandingkan dengan metode MWFTS-PSO, saat diintegrasikan dengan metode MWFTS. ***** Markov Weighted Fuzzy Time Series (MWFTS) is a forecasting method that combines the concept of fuzzy time series with the Markov model. This study aims to compare the performance of MWFTS optimized using Particle Swarm Optimization (PSO) and Cat and Mouse Based Optimizer (CMBO) for Ethereum price forecasting. Both optimization algorithms were employed to optimize the interval boundaries of the MWFTS model. The data used consisted of secondary data in the form of daily Ethereum closing prices from January 1, 2025, to March 31, 2026, obtained from id.investing.com. In this study, the data were divided into training and testing datasets with a ratio of 8:2, where the entire optimization process was performed using the training dataset, while the testing dataset was used to evaluate the prediction accuracy of the models. The results show that the application of PSO and CMBO improves the performance of MWFTS compared with the original MWFTS model without optimization. Based on the comparative results, the MWFTS-CMBO optimization achieves lower error values, with MAE (172.02), MAPE (7.58%), and RMSE (207.66), compared with MWFTS-PSO, which obtains MAE (191.47), MAPE (8.57%), and RMSE (226.46). These results indicate that MWFTS-CMBO provides more accurate forecasting results than MWFTS-PSO when integrated with the MWFTS method.

Item Type:	Thesis (Sarjana)
Additional Information:	1). Drs. Sudarwanto, M.Si., DEA ; 2). Devi Eka Wardani M., S.Pd., M.Si.
Subjects:	Sains > Matematika
Divisions:	FMIPA > S1 Matematika
Depositing User:	Ilham Hargo Sujanto .
Date Deposited:	27 Aug 2026 03:32
Last Modified:	27 Aug 2026 03:32
URI:	http://repository.unj.ac.id/id/eprint/73323

Actions (login required)

View Item