Prediksi Harga Bitcoin Menggunakan Metode HMM-LSTM

Nafie, Rayya Ruwa'im (2025) Prediksi Harga Bitcoin Menggunakan Metode HMM-LSTM. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text 21081010119.-cover.pdf Download (1MB)
	Text (Bab 1) 21081010119.-bab1.pdf Download (24kB)
	Text (Bab 2) 21081010119.-bab2.pdf Restricted to Repository staff only until 12 December 2027. Download (568kB) \| Request a copy
	Text (Bab 3) 21081010119.-bab3.pdf Restricted to Repository staff only until 12 December 2027. Download (624kB) \| Request a copy
	Text (Bab 4) 21081010119.-bab4.pdf Restricted to Repository staff only until 12 December 2027. Download (2MB) \| Request a copy
	Text (Bab 5) 21081010119.-bab5.pdf Download (14kB)
	Text (Daftar Pustaka) 21081010119.-daftarpustaka.pdf Download (96kB)
	Text (Lampiran) 21081010119.-lampiran.pdf Restricted to Repository staff only until 12 December 2027. Download (111kB) \| Request a copy

Abstract

The rapid advancement of technology has driven the emergence of digital assets such as cryptocurrencies, creating new opportunities and challenges in modern investment. One of the most prominent cryptocurrencies is Bitcoin, often referred to as digital gold due to its scarcity and decentralized nature. However, the high volatility of Bitcoin prices makes prediction difficult and risky for investors. Therefore, this study aims to predict Bitcoin prices using the Hybrid Hidden Markov Model–Long Short-Term Memory (HMM-LSTM) method, which combines the HMM’s ability to detect market regime changes with the LSTM’s capability to learn non-linear patterns in time-series data. The experimental results show that the HMM-LSTM model outperforms the standalone LSTM model, achieving MAE of 1080.0855, RMSE of 1594.6266, and MAPE of 2.00%, while the LSTM model produced MAE of 1678.2953, RMSE of 2298.2291, and MAPE of 2.95%. Based on these findings, the HMM-LSTM model demonstrates higher accuracy and stability in predicting Bitcoin prices and can serve as a reliable reference for developing predictive analysis systems and supporting decision-making in the financial and digital asset investment sectors.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Sari, Anggraini Puspita	NIDN0716088605	anggraini.puspita.if@upnjatim.ac.id
Thesis advisor	Junaidi, Achmad	NIDN0019067008	achmadjunaidi.if@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA76.6 Computer Programming
T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Rayya Nafie

Date Deposited:

08 Dec 2025 04:42

Last Modified:

08 Dec 2025 04:42

URI:

https://repository.upnjatim.ac.id/id/eprint/48172