DEWI, RATNASARI WIJAYA (2023) PERAMALAN HARGA MINYAK MENTAH BRENT MENGGUNAKAN CASCADE FORWARD NEURAL NETWORK. Sarjana / Sarjana Terapan (S1/D4) thesis, Universitas Muhammadiyah Semarang.
|
Text
1. Halaman Depan.pdf Download (575kB) | Preview |
|
|
Text
5. ABSTRAK_ABSTRACT.pdf Download (451kB) | Preview |
|
|
Text
11. BAB 1.pdf Download (865kB) | Preview |
|
|
Text
12. BAB 2.pdf Download (926kB) | Preview |
|
Text
13. BAB 3.pdf Restricted to Repository staff only Download (509kB) | Request a copy |
||
Text
14. BAB 4.pdf Restricted to Repository staff only Download (988kB) | Request a copy |
||
|
Text
15. BAB 5.pdf Download (452kB) | Preview |
|
|
Text
16. Daftar Pustaka.pdf Download (525kB) | Preview |
|
Text
18. Lampiran.pdf Restricted to Repository staff only Download (1MB) | Request a copy |
||
Text
19. FULL TEXT SKRIPSI_DEWI RATNASARI WIJAYA B2A221002.pdf Restricted to Repository staff only Download (4MB) | Request a copy |
Abstract
ABSTRAK Dewi Ratnasari Wijaya, 2023. Peramalan Harga Minyak Mentah Brent Menggunakan Cascade Forward Neural Network. Skripsi, Program Studi Statistika, Universitas Muhammadiyah Semarang. Pembimbing I: Tiani Wahyu Utami, M.Si., Pembimbing II: Fatkhurokhman Fauzi, M.Stat. Minyak mentah menjadi salah satu produk atau komoditas non-pangan yang paling banyak diperjual-belikan di dunia saat ini. Bahkan di Indonesia, minyak mentah masih menjadi sektor paling berpengaruh dalam Produk Domestik Bruto tahun 2021. Konsumsi bahan bakar minyak (BBM) di Indonesia yang berlebih menjadikan minyak mentah terutaman jenis solar menjadi langka. Salah satu upaya penting untuk mengatisipasi terjadinya fluktuasi harga bahan bakar minyak adalah dengan monitoring dan peramalan harga minyak mentah jenis brent. Jenis data yang memiliki pola yang tidak teratur bisa diatasi menggunakan metode Neural Network. Cascade Forward Neural Network (CFNN) merupakan jaringan syaraf tiruan yang memiliki arsitektur mirip dengan Feed Forward Neural Netwok (FFNN), tetapi terdapat hubungan langsung antara input dan output. Tujuan dari penelitian ini adalah untuk mengetahui gambaran umum harga minyak mentah brent dari januari 2008 sampai desember 2022 dan meramalkan harga brent selama 12 periode kedepan dengan metode CFNN. Hasil penelitian menunjukkan bahwa gambaran umum harga minyak mentah brent mengalami fluktuatif harga dari tahun ke tahun. Hasil pelatihan jaringan telah didapatkan model arsitektur terbaiknya yaitu 2-6-1 dan diperoleh MAPE trainingnya sebesar 6,3473% dan MAPE pada testingnya sebesar 9,4689% dan kurang dari 10% yang artinya model tersebut memiliki kemampuan peramalan yang sangat baik. Kata Kunci: Artificial Neural Network, Cascade Forward, Brent, Minyak Mentah, MAPE. ABSTRACT Dewi Ratnasari Wijaya, 2023. Brent Crude Oil Price Forecasting Using Cascade Forward Neural Network. Thesis, Undergraduate Statistics Study Program, University of Muhammadiyah Semarang. Supervisor I : Tiani Wahyu Utami, M.Si., Supervisor II: Fatkhurokhman Fauzi, M.Stat. Crude oil is one of the most traded non-food products or commodities in the world today. Even in Indonesia, crude oil is still the most influential sector in the Gross Domestic Product in 2021. Excessive consumption of fuel oil (BBM) in Indonesia makes crude oil, especially the diesel type, scarce. One important effort to anticipate fluctuations in the price of fuel oil is monitoring and forecasting the price of brent crude oil. Types of data that have irregular patterns can be overcome using the Neural Network method. Cascade Forward Neural Network (CFNN) is an artificial neural network that has an architecture similar to the Feed Forward Neural Network (FFNN), but there is a direct relationship between input and output. The purpose of this study is to find out the general description of the price of brent crude oil from January 2008 to December 2022 and to forecast the price of brent for the next 12 periods using the CFNN method. The results of the study show that the general picture of Brent crude oil prices fluctuates from year to year. The results of network training have obtained the best architectural model, namely 2-6-1 and obtained MAPE training of 6.3473% and MAPE in Testing of 9.4689% and less than 10%, which means that the model has very good forecasting capabilities. Keyword: Artificial Neural Network, Cascade Forward, Brent, Crude Oil, MAPE
Item Type: | Thesis (Sarjana / Sarjana Terapan (S1/D4) ) |
---|---|
Call Number: | 018/Statistika/VII/2023 |
Subjects: | L Education > Statistics |
Divisions: | Faculty of Agricultural Science and Technology > S1 Statistics |
Depositing User: | perpus unimus |
Date Deposited: | 14 Jul 2023 08:20 |
Last Modified: | 14 Jul 2023 08:20 |
URI: | http://repository.unimus.ac.id/id/eprint/7118 |
Actions (login required)
View Item |