Integrasi Data Historis Dan Sentimen Pasar Dalam Prediksi Harga Bitcoin Menggunakan Indo RoBERTa Finansial-BiGRU

Alesandro, Alesandro Yoel Deca Putranto (2026) Integrasi Data Historis Dan Sentimen Pasar Dalam Prediksi Harga Bitcoin Menggunakan Indo RoBERTa Finansial-BiGRU. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 2043221136-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (6MB) | Request a copy

Abstract

Volatilitas ekstrem Bitcoin menyulitkan prediksi harga yang akurat, sehingga memerlukan pendekatan hibrida yang menggabungkan data historis dan sentimen pasar. Penelitian ini bertujuan mengembangkan model prediksi harga Bitcoin dengan mengintegrasikan Indo RoBERTa Financial untuk analisis sentimen berita berbahasa Indonesia dan Bidirectional Gated Recurrent Unit (BiGRU) untuk pemodelan time-series. Data kuantitatif mencakup harga penutupan Bitcoin, GLD, S&P 500, NASDAQ 100, dan volume perdagangan periode 1 Januari 2024–30 September 2025 yang diperoleh dari Investing.com. Data teks berupa 8.818 artikel berita dari CNBC Indonesia, Detik.com, dan Tokocrypto dianalisis sentimennya menggunakan Indo RoBERTa Financial. Hasil menunjukkan model faktor eksternal (X1-X5) menghasilkan performa terbaik dengan MAPE 1,90%, mengungguli model teknis (2,02%), dan model hibrida (2,71%). Temuan ini membuktikan bahwa integrasi data historis Bitcoin dengan indikator faktor eksternal memberikan prediksi lebih akurat dibandingkan pendekatan berbasis sentimen berita semata. Sentimen berita lokal memiliki noise tinggi dan kurang relevan untuk prediksi jangka pendek Bitcoin. Model terbaik menghasilkan prediksi harga Bitcoin 1 Oktober 2025 sebesar $113,723.70, dengan implikasi praktis sebagai alat bantu keputusan investasi yang andal untuk trader institusional maupun ritel.
==============================================================================================================================
Bitcoin's extreme volatility complicates accurate price forecasting, necessitating a hybrid approach combining historical data and market sentiment analysis. This study develops a Bitcoin price prediction model by integrating Indo RoBERTa Financial for sentiment analysis of Indonesian financial news and Bidirectional Gated Recurrent Unit (BiGRU) for time-series modeling. Quantitative data includes Bitcoin closing prices, GLD, S&P 500, NASDAQ 100, and trading volume from January 1, 2024 to September 30, 2025, sourced from Investing.com. Text data comprises 8,818 news articles from CNBC Indonesia, Detik.com, and Tokocrypto, analyzed for sentiment using Indo RoBERTa Financial. Results show the external factor model (X1-X5) achieves optimal performance with MAPE of 1.90%, outperforming the technical model (2.02%), and hybrid model (2.71%). These findings confirm that integrating Bitcoin's historical data with macroeconomic indicators yields more accurate predictions than sentiment-only approaches. Local news sentiment contains substantial noise and limited relevance for short-term Bitcoin forecasting. The optimal model predicts Bitcoin's price for October 1, 2025 at $113,723.70, offering a reliable decision-support tool for institutional and retail investors seeking to navigate cryptocurrency market volatility through data-driven strategies.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Analisis Sentimen, BiGRU, Bitcoin, Deep Learning, GRU.========== Bitcoin, BIGRU, Deep Learning, GRU, Sentiment Analysis
Subjects:	H Social Sciences > H Social Sciences (General) > H61.4 Forecasting in the social sciences H Social Sciences > HA Statistics > HA30.3 Time-series analysis H Social Sciences > HA Statistics > HA31.3 Regression. Correlation. Logistic regression analysis. H Social Sciences > HA Statistics > HA31.7 Estimation H Social Sciences > HB Economic Theory > Economic forecasting--Mathematical models. H Social Sciences > HC Economic History and Conditions > HC441 Macroeconomics. Q Science > Q Science (General) > Q180.55.M38 Mathematical models Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression Q Science > QA Mathematics > QA336 Artificial Intelligence Q Science > QA Mathematics > QA401 Mathematical models. Q Science > QA Mathematics > QA76.585 Cloud computing. Mobile computing. Q Science > QA Mathematics > QA76.6 Computer programming. Q Science > QA Mathematics > QA76.625 Internet programming. Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) Q Science > QA Mathematics > QA76.9 Computer algorithms. Virtual Reality. Computer simulation. Q Science > QA Mathematics > QA76.9.D33 Data compression (Computer science) Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science) Q Science > QA Mathematics > QA76.9D338 Data integration Q Science > QA Mathematics > QA76.F56 Data structures (Computer science) T Technology > T Technology (General) > T174 Technological forecasting T Technology > T Technology (General) > T385 Visualization--Technique T Technology > T Technology (General) > T57.5 Data Processing T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models. T Technology > T Technology (General) > T58.62 Decision support systems
Divisions:	Faculty of Vocational > 49501-Business Statistics
Depositing User:	Alesandro Yoel Deca Putranto
Date Deposited:	13 Apr 2026 00:38
Last Modified:	13 Apr 2026 00:38
URI:	http://repository.its.ac.id/id/eprint/132778

Actions (login required)

View Item