Thông tin chung
  English
  Đề tài NC khoa học
  Bài báo, báo cáo khoa học
  Hướng dẫn Sau đại học
  Sách và giáo trình
  Các học phần và môn giảng dạy
  Giải thưởng khoa học, Phát minh, sáng chế
  Khen thưởng
  Thông tin khác
  Tài liệu tham khảo
  Hiệu chỉnh
 
Số người truy cập: 168,569,851

 An Empirical Study on Bitcoin Price Prediction using Deep Learning
Tác giả hoặc Nhóm tác giả: Ngoc Tho Huynh, Thi Minh Phuong Ha, Duy Khanh Nguyen, Khanh Duy Dao, Thi Kim Ngan Dang
Nơi đăng: International conference on Digital Economy and Fintech Innovation 2025; Số: 1;Từ->đến trang: 1-8;Năm: 2025
Lĩnh vực: Công nghệ thông tin; Loại: Bài báo khoa học; Thể loại: Quốc tế
TÓM TẮT
Bitcoin has demonstrated consistent growth in value, garnering substantial recognition and attracting significant investment. Specifically, the price of Bitcoin has witnessed an upward trend, consistently reaching new historical highs. In order to support decision-making for investors and guide macroeconomic strategic planning, a variety of predictive methods have been employed to predict fluctuations in Bitcoin's price. These price changes are influenced by numerous factors. This paper introduces a new aspect of the dataset that affects Bitcoin's price and experiments with several deep learning models combined with optimization algorithms to identify an effective deep learning model for predicting Bitcoin price movements based on the characteristics of the proposed dataset. The experimental results demonstrate that the Convolutional Neural Network achieved the most significant performance among the evaluated models for predicting Bitcoin prices.
ABSTRACT
Bitcoin has demonstrated consistent growth in value, garnering substantial recognition and attracting significant investment. Specifically, the price of Bitcoin has witnessed an upward trend, consistently reaching new historical highs. In order to support decision-making for investors and guide macroeconomic strategic planning, a variety of predictive methods have been employed to predict fluctuations in Bitcoin's price. These price changes are influenced by numerous factors. This paper introduces a new aspect of the dataset that affects Bitcoin's price and experiments with several deep learning models combined with optimization algorithms to identify an effective deep learning model for predicting Bitcoin price movements based on the characteristics of the proposed dataset. The experimental results demonstrate that the Convolutional Neural Network achieved the most significant performance among the evaluated models for predicting Bitcoin prices.
© Đại học Đà Nẵng
 
 
Địa chỉ: 41 Lê Duẩn Thành phố Đà Nẵng
Điện thoại: (84) 0236 3822 041 ; Email: dhdn@ac.udn.vn