Pemodelan Harga Cryptocurrency Menggunakan Markov Switching Autoregressive

Ashariansyah, Akhmad Ridho (2020) Pemodelan Harga Cryptocurrency Menggunakan Markov Switching Autoregressive. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[img] Text
06211640000089-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only

Download (1MB) | Request a copy

Abstract

Perdagangan merupakan sebuah kegiatan tukar menukar barang atau jasa yang dilakukan manusia untuk memenuhi kebutuhan hidup. Sejarah alat perdagangan manusia dimulai dari sistem pertukaran barang atau barter, kemudian tercipta uang kartal dan giral, sampai munculnya uang elektronik. Seiring dengan perkembangan teknologi, muncul kekhawatiran penyalahgunaan harta serta data pada uang elektronik oleh pihak ketiga. Cryptocurrency hadir sebagai metode pembayaran digital bersistem kriptografi serta dapat menjaga kerahasiaan data pemiliknya karena tidak bisa dilacak oleh pihak ketiga lainnya. Bitcoin menjadi pionir munculnya cryptocurrency terdesen-tralisasi sepenuhnya. Cryptocurrency tidak sepenuhnya bagus, namun terdapat pergerakan harga yang sangat cepat dari waktu ke waktu. Faktor penyebab fluktuasi harga cryptocurrency yaitu adanya batas ketersediaan pasokan koin. Fluktuasi harga cryptocurrency dapat merubah harga secara signifikan dalam waktu yang sangat cepat, hal ini menyebabkan pola data yang berubah-ubah dari waktu ke waktu. Pola data yang berubah-ubah dapat diselesaikan dengan metode Markov Switching Autoregressive (MSAR) menggunakan algoritma EM (Expectation Maximization) agar meminimalisir risiko kerugian pemilik aset kripto. Data yang digunakan adalah data sekunder harga harian tiga jenis cryptocurrency dengan nilai kapitalisasi pasar terbesar. Hasil penelitian menunjukkan bahwa bitcoin dan ripple menggunakan model MS(8)AR(1) dan ethereum menggunakan model MS(9)AR(1). Hasil klasifikasi state ripple memiliki nilai akurasi lebih tinggi dibandingkan bitcoin dan ethereum. ============================================================ ============================================================ Trade is an activity of buying and selling goods or services carried out by humans to meet the necessities of life. The history of trading tools starts from barter systems, then creates currency and demand deposits, until the emergence of electronic money. As technology develops, there are concerns about the misuse of property and data on electronic money by third parties. Cryptocurrency comes as a cryptographic digital payment method and can maintain the confidentiality of the owner's data because it cannot be tracked by other third parties. Bitcoin pioneered the emergence of fully decentralized cryptocurrency. Cryptocurrency is not entirely good, but there are price movements that are very fast from time to time. Factors causing cryptocurrency price fluctuations are the limited supply of coins. Cryptocurrency price fluctuations can change prices significantly in a very fast time, this causes data patterns to change from time to time. Changing data patterns can be solved using the Markov Switching Autoregressive (MSAR) method using the EM (Expectation Maximization) algorithm in order to minimize the risk of loss to the owners of crypto assets. The data used are secondary data on daily prices of three types of cryptocurrency with the largest market capitalization value. The study conducted show that bitcoin and ripple using MS(8)AR(1) model and ethereum used the MS(9)AR(1) model. The ripple state model classification results have a higher accuracy value than bitcoin and ethereum.

Item Type: Thesis (Undergraduate)
Additional Information: RSSt 519.536 Ash p-1 • Ashariansyah, Akhmad Ridho
Uncontrolled Keywords: Cryptocurrency, Fluktuasi, MSAR, Cryptocurrency, Fluctuacy, MSAR
Subjects: H Social Sciences > HA Statistics > HA30.3 Time-series analysis
Q Science > QA Mathematics > QA274.7 Markov processes--Mathematical models.
Divisions: Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User: Akhmad Ridho Ashariansyah
Date Deposited: 28 Aug 2020 02:59
Last Modified: 19 Oct 2020 04:16
URI: https://repository.its.ac.id/id/eprint/81467

Actions (login required)

View Item View Item