Perbandingan Metode Fuzzy Time Series Markov Chain dan Hidden Markov Model Untuk Memprediksi Harga Minyak Mentah

Salam, Navilah Rizqy (2019) Perbandingan Metode Fuzzy Time Series Markov Chain dan Hidden Markov Model Untuk Memprediksi Harga Minyak Mentah. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 06111540000041-Undergraduate_Theses.pdf Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

Minyak mentah merupakan salah satu komoditas terbesar dan berpengaruh pada perekonomian global. Naik turunnya (fluktuasi) harga minyak mentah dapat berpengaruh bagi negara konsumen maupun negara produsen. Oleh karenanya, prediksi harga minyak mentah dirasa penting untuk membantu dalam pengambilan keputusan bagi para investor atau negara yang bersangkutan. Bagi Indonesia sendiri hal ini dapat berpengaruh dalam penyusunan Anggaran Pendapatan dan Belanja Negara (APBN) dalam menyediakan subsidi rakyatnya. Dalam Tugas Akhir ini dibandingkan dua metode peramalan untuk memprediksi harga minyak mentah. Metode-metode tersebut yaitu Fuzzy Time Series Markov Chain (FTSMC) dan Hidden Markov Model (HMM). Diantara kedua metode tersebut didapatkan hasil bahwa metode Fuzzy Time Series Markov Chain (FTSMC) lebih baik dalam prediksi harga minyak mentah dengan akurasi yang tinggi berdasarkan nilai ketepatan metode peramalan Mean Absolute Percentage Error (MAPE) sebesar 4.486%.
=============================================================================================================================
Crude oil is one of the biggest commodities and influences the global economy. Fluctuations (fluctuations) in the price of crude oil can affect both the consumer country and the producing country. Therefore, the prediction of crude oil prices is considered important to assist in making decisions for investors or the country concerned. For Indonesia, this can affect the preparation of the State Budget (APBN) in providing subsidies for its people. In this Final Project two forecasting methods was compared to predict the price of crude oil. These methods are Fuzzy Time Series Markov Chain (FTSMC) and Hidden Markov Model (HMM). Among the two methods, it was found that the Fuzzy Time Series Markov Chain (FTSMC) method is better in predicting crude oil prices with high accuracy based on the accuracy value of the forecasting method of Mean Absolute Percentage Error (MAPE) is 4.486%.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Minyak mentah, peramalan, FTSMC, HMM, MAPE.
Subjects:	Q Science > QA Mathematics > QA274.2 Stochastic analysis Q Science > QA Mathematics > QA274.7 Markov processes--Mathematical models. Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA248_Fuzzy Sets
Divisions:	Faculty of Mathematics and Science > Mathematics > 44201-(S1) Undergraduate Thesis
Depositing User:	Navilah Rizqy Salam
Date Deposited:	06 Aug 2026 03:05
Last Modified:	06 Aug 2026 03:05
URI:	http://repository.its.ac.id/id/eprint/66085

Actions (login required)

View Item