4.7 Article

A Comparative Study of Bitcoin Price Prediction Using Deep Learning

期刊

MATHEMATICS
卷 7, 期 10, 页码 -

出版社

MDPI
DOI: 10.3390/math7100898

关键词

bitcoin; blockchain; cryptocurrency; deep learning; predictive model; time series analysis

资金

  1. National Research Foundation of Korea (NRF) - Korea government (MSIT) [2019R1F1A1063272]
  2. Kangwon National University
  3. National Research Foundation of Korea [2019R1F1A1063272] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)

向作者/读者索取更多资源

Bitcoin has recently received a lot of attention from the media and the public due to its recent price surge and crash. Correspondingly, many researchers have investigated various factors that affect the Bitcoin price and the patterns behind its fluctuations, in particular, using various machine learning methods. In this paper, we study and compare various state-of-the-art deep learning methods such as a deep neural network (DNN), a long short-term memory (LSTM) model, a convolutional neural network, a deep residual network, and their combinations for Bitcoin price prediction. Experimental results showed that although LSTM-based prediction models slightly outperformed the other prediction models for Bitcoin price prediction (regression), DNN-based models performed the best for price ups and downs prediction (classification). In addition, a simple profitability analysis showed that classification models were more effective than regression models for algorithmic trading. Overall, the performances of the proposed deep learning-based prediction models were comparable.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

Article Computer Science, Information Systems

Optimizing skyline queries over incomplete data

Jongwuk Lee, Hyeonseung Im, Gae-won You

INFORMATION SCIENCES (2016)

Article Computer Science, Artificial Intelligence

Computing Exact Skyline Probabilities for Uncertain Databases

Dongwon Kim, Hyeonseung Im, Sungwoo Park

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2012)

Article Computer Science, Information Systems

The Farthest Spatial Skyline Queries

Gae-won You, Mu-Woong Lee, Hyeonseung Im, Seung-won Hwang

INFORMATION SYSTEMS (2013)

Article Chemistry, Analytical

Measurement Noise Recommendation for Efficient Kalman Filtering over a Large Amount of Sensor Data

Sebin Park, Myeong-Seon Gil, Hyeonseung Im, Yang-Sae Moon

SENSORS (2019)

Article Computer Science, Theory & Methods

Backward type inference for XML queries

Hyeonseung Im, Pierre Geneves, Nils Gesbert, Nabil Layaida

THEORETICAL COMPUTER SCIENCE (2020)

Article Mathematics

On Correspondence between Selective CPS Transformation and Selective Double Negation Translation

Hyeonseung Im

Summary: This paper discusses the method of embedding classical logic into intuitionistic logic using double negation translation, as well as continuation passing style transformation implemented through the Curry-Howard isomorphism in programming languages. By selectively translating nontrivial expressions into CPS functions using a type and effect system, a logical account of CBV selective CPS transformation is provided. The selective DNT derived from the corresponding type and effect system can translate classical proofs into equivalent intuitionistic proofs, presenting a smaller scale compared to traditional DNTs.

MATHEMATICS (2021)

Article Chemistry, Analytical

Anisotropic SpiralNet for 3D Shape Completion and Denoising

Seong Uk Kim, Jihyun Roh, Hyeonseung Im, Jongmin Kim

Summary: Three-dimensional mesh post-processing is crucial due to hardware limitations and imperfect capture environments. In this study, we propose a novel approach utilizing a deep learning framework to complete and denoise 3D mesh data. Experimental results demonstrate improved reconstruction quality and higher accuracy compared to previous neural network systems.

SENSORS (2022)

Article Computer Science, Information Systems

Evaluating Countermeasures for Verifying the Integrity of Ethereum Smart Contract Applications

Suhwan Ji, Dohyung Kim, Hyeonseung Im

Summary: This paper discusses the evolution of blockchain technology, DApps, and vulnerabilities in smart contracts. A software tool is proposed to evaluate and select the most effective countermeasures for vulnerabilities, revealing trade-offs in detecting vulnerabilities.

IEEE ACCESS (2021)

Article Computer Science, Information Systems

Clinical Implication of Machine Learning in Predicting the Occurrence of Cardiovascular Disease Using Big Data (Nationwide Cohort Data in Korea)

Gihun Joo, Yeongjin Song, Hyeonseung Im, Junbeom Park

IEEE ACCESS (2020)

Proceedings Paper Computer Science, Information Systems

A Core Calculus for XQuery 3.0 Combining Navigational and Pattern Matching Approaches

Giuseppe Castagna, Hyeonseung Im, Kim Nguyen, Veronique Benzaken

PROGRAMMING LANGUAGES AND SYSTEMS (2015)

Article Computer Science, Software Engineering

Polymorphic Functions with Set-Theoretic Types Part 1: Syntax, Semantics, and Evaluation

Giuseppe Castagna, Kim Nguyen, Zhiwu Xu, Hyeonseung Im, Serguei Lenglet, Luca Padovani

ACM SIGPLAN NOTICES (2014)

Proceedings Paper Computer Science, Information Systems

Contractive Signatures with Recursive Types, Type Parameters, and Abstract Types

Hyeonseung Im, Keiko Nakata, Sungwoo Park

AUTOMATA, LANGUAGES, AND PROGRAMMING, PT II (2013)

暂无数据