Peramalan Nilai Tukar GBP/USD Dengan Metode Self-Exciting Threshold Autoregressive (SETAR) DAN Markov Switching Autoregressive (MSAR)

Sitorus, Jonathan Mangasi (2023) Peramalan Nilai Tukar GBP/USD Dengan Metode Self-Exciting Threshold Autoregressive (SETAR) DAN Markov Switching Autoregressive (MSAR). Other thesis, Institut Teknologi Sepuluh Nopember.

Text 06211940000126-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (2MB) | Request a copy

Abstract

Foreign Exchange (forex) adalah konversi mata uang suatu negara secara internasional yang mempunyai catatan kurs resmi pada bank sentral masing-masing negara. Pasar forex merupakan pasar keuangan terbesar di dunia dibandingkan dengan pasar keuangan lainnya, seperti pasar saham, pasar obligasi, pasar komoditas, pasar kripto, dan pasar derivatif berdasarkan data dari BIS. Pasangan mata uang asing yang menjadi favorit dalam trading forex salah satunya yaitu nilai tukar mata uang GBP/USD. Pada penelitian ini akan dilakukan perbandingan model SETAR dan MSAR dalam meramalkan nilai tukar mata uang GBP/USD mulai dari 1 Juni 2022 sampai 20 Februari 2023. Metode SETAR dan MSAR dapat diaplikasikan pada data finansial. Model SETAR menggunakan threshold yang berfungsi sebagai pemisah antar regime, sedangkan model MSAR dapat memodelkan ketidakstabilan dalam data dengan menggunakan model Markov untuk memperhitungkan adanya perubahan keadaan atau regime. Hasil yang didapatkan pada penelitian ini adalah model terbaik untuk memodelkan nilai tukar GBP/USD adalah SETAR (1,4,1) dan MS(3)AR(1). Pada penelitian ini juga didapatkan hasil bahwa model MSAR dapat memberikan hasil ramalan yang lebih akurat dibandingkan model SETAR jika menggunakan One-step ahead forecast, namun jika menggunakan teknik N-step ahead forecast model SETAR memberikan hasil ramalan yang lebih akurat untuk meramalkan nilai tukar GBP/USD periode 1 Juni 2022 sampai 20 Februari 2023.
===============================================================================================================================
Foreign Exchange (forex) is the international conversion of a country's currency, which has official exchange rates recorded by each country's central bank. The forex market is the largest financial market in the world compared to other financial markets such as the stock market, bond market, commodity market, cryptocurrency market, and derivative market according to BIS data. One of the favorite foreign currency pairs in forex trading is the GBP/USD exchange rate. This study will compare the SETAR and MSAR models in forecasting the GBP/USD exchange rate from June 1, 2022, to February 20, 2023. The SETAR and MSAR methods can be applied to financial data. The SETAR model uses thresholds as separators between regimes, while the MSAR model can model instability in data by using a Markov model to account for changes in conditions or regimes. The results obtained from this study indicate that the best model for modeling the GBP/USD exchange rate is SETAR (1,4,1) and MS(3)AR(1). This study also found that the MSAR model provides more accurate forecasting results compared to the SETAR model when using a one-step ahead forecast. However, when using the N-step ahead forecast technique, the SETAR model provides more accurate forecasting results for predicting the GBP/USD exchange rate for the period from June 1, 2022, to February 20, 2023.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	MSAR, SETAR, Forex, Peramalan, MSAR, SETAR, Forex, Forecast
Subjects:	H Social Sciences > HA Statistics > HA30.3 Time-series analysis H Social Sciences > HG Finance > HG3881 Foreign exchange.
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Jonathan Mangasi Sitorus
Date Deposited:	05 Sep 2023 05:36
Last Modified:	05 Sep 2023 05:36
URI:	http://repository.its.ac.id/id/eprint/104671

Actions (login required)

View Item