Prediksi harga opsi jual dan beli pada aset bitcoin dan s&p 500 menggunakan machine learning dan simulasi monte carlo = Prediction of European call and put option prices on bitcoin and s&p 500 assets using machine learning and monte carlo simulation

Wibisono, Shannen Surya (2025) Prediksi harga opsi jual dan beli pada aset bitcoin dan s&p 500 menggunakan machine learning dan simulasi monte carlo = Prediction of European call and put option prices on bitcoin and s&p 500 assets using machine learning and monte carlo simulation. Bachelor thesis, Universitas Pelita Harapan.

[thumbnail of Title] Text (Title)
Title.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (334kB)
[thumbnail of Abstract] Text (Abstract)
Abstract.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (740kB)
[thumbnail of TOC] Text (TOC)
TOC.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (810kB)
[thumbnail of Chapter 1] Text (Chapter 1)
Chapter 1.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (742kB)
[thumbnail of Chapter 2] Text (Chapter 2)
Chapter 2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[thumbnail of Chapter 3] Text (Chapter 3)
Chapter 3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (945kB)
[thumbnail of Chapter 4] Text (Chapter 4)
Chapter 4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (3MB)
[thumbnail of Chapter 5] Text (Chapter 5)
Chapter 5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (735kB)
[thumbnail of Bibliography] Text (Bibliography)
Bibliography.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (743kB)
[thumbnail of Appendices] Text (Appendices)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (2MB)

Abstract

Opsi merupakan instrumen keuangan yang digunakan sebagai lindung nilai terhadap perubahan harga aset dasar, seperti saham, indeks saham, dan mata uang kripto. Penelitian ini membandingkan metode machine learning (XGBoost dan LightGBM) dengan simulasi Monte Carlo dalam memprediksi harga opsi Eropa. Perbedaan utama antara kedua pendekatan terletak pada pembagian data, di mana metode machine learning menggunakan data acak, sementara simulasi Monte Carlo memanfaatkan urutan data berdasarkan waktu. Selain itu, simulasi Monte Carlo menghasilkan rentang percentile 5% hingga 95%, sedangkan machine learning memberikan satu nilai prediksi harga opsi. Hasil penelitian menunjukkan bahwa pada metode machine learning, XGBoost memiliki nilai RMSE dan MAPE yang lebih rendah dibandingkan LightGBM di sebagian besar datasetr. Pendekatan dengan /ag jangka pendek lebih relevan untuk Bitcoin, sedangkan /ag jangka panjang lebih sesuai untuk S&P 500. Hal ini dikarenakan volatilitas yang tinggi waktu yang pada Bitcoin cenderung lebih sensitif terhadap penghitungan volatilitas dengan interval lebih pendek. = Sementara itu, simulasi Carlo menghasilkan rentang percentile 5% hingga 95% sebagai acuan prediksi harga opsi, dengan skema partisi data 60/40 terbukti lebih optimal dibandingkan skema 5 Monte hari sebelum jatuh tempo dan 80/20. Secara keseluruhan, baik metode machine learning maupun simulasi Monte Carlo menunjukkan bahwa prediksi opsi untuk aset Bitcoin lebih akurat dibandingkan S&P 500, dan prediksi opsi call lebih baik dibandingkan opsi pus. Temuan ini memberikan panduan bagi penerbit opsi dan investor dalam memilih metode prediksi yang tepat untuk berbagai jenis aset, termasuk Bitcoin dan S&P 500, guna mendukung pengambilan keputusan investasi yang lebih baik. / Options are financial instruments used to hedge against price fluctuations in underlying assets such as stocks, stock indices, and cryptocurrencies. This study compares the machine learning methods (XGBoost and LightGBM) with Monte Carlo simulation in predicting European option prices. The key difference between the data, two approaches lies in data partitioning: machine learning utilizes random while Monte Carlo simulation follows a time-ordered sequence. Additionally, Monte Carlo simulation produces a 5% to 95% percentile range, whereas machine learning provides a single predicted price. The results indicate that, in machine learning, XGBoost achieves lower RMSE and MAPE values compared to LightGBM across most datasets. Short-term /ags are more relevant for Bitcoin, whereas long-term /ags are more suitable for the S&P 500 due to Bitcoin’s high volatility, which is better captured by shorter time intervals. Meanwhile, Monte Carlo simulation produces a 5% to 95% percentile range as a reference for option prices, with a 60/40 data split proving to be the most optimal compared to a 5-day pre-maturity split and an 80/20 split. Overall, both machine learning and Monte Carlo simulation demonstrate that option predictions for Bitcoin are more accurate than those for the S&P 500, and call options perform better than put options. These findings provide valuable insights for option issuers and investors in selecting appropriate prediction methods for various assets, including Bitcoinand the S&P 500, to-support better investment decision-making.
Item Type: Thesis (Bachelor)
Creators:
Creators
NIM
Email
ORCID
Wibisono, Shannen Surya
NIM01112210013
shannenswibisono@gmail.com
UNSPECIFIED
Contributors:
Contribution
Contributors
NIDN/NIDK
Email
Thesis advisor
Margaretha, Helena
NIDN0312057504
helena.margaretha@uph.edu
Thesis advisor
Widjaja, Petrus
NIDN0314095901
petrus.widjaja@lecturer.uph.edu
Uncontrolled Keywords: prediksi harga opsi Eropa; metode pembelajaran mesin; simulasi Monte Carlo; XGBoost; LightGBM; European option price prediction; machine learning methods; Monte Carlo simulation; XGBoost; LightGBM.
Subjects: Q Science > QA Mathematics
Divisions: University Subject > Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Mathematics
Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Mathematics
Depositing User: Stefanus Tanjung
Date Deposited: 10 Aug 2025 02:15
Last Modified: 10 Aug 2025 02:15
URI: http://repository.uph.edu/id/eprint/70437

Actions (login required)

View Item
View Item