• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.10
• /
• pp.387-396
• /
• 2018

Stock price prediction has been a difficult problem to solve. There have been many studies to predict stock price scientifically, but it is still impossible to predict the exact price. Recently, a variety of types of cryptocurrency has been developed, beginning with Bitcoin, which is technically implemented as the concept of distributed ledger. Various approaches have been attempted to predict the price of cryptocurrency. Especially, it is various from attempts to stock prediction techniques in traditional stock market, to attempts to apply deep learning and reinforcement learning. Since the market for cryptocurrency has many new features that are not present in the existing traditional stock market, there is a growing demand for new analytical techniques suitable for the cryptocurrency market. In this study, we first collect and process seven cryptocurrency price data through Bithumb's API. Then, we use the gradient boosting model, which is a data-driven learning based machine learning model, and let the model learn the price data change of cryptocurrency. We also find the most optimal model parameters in the verification step, and finally evaluate the prediction performance of the cryptocurrency price trends.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.45-55
• /
• 2022

The size of the cryptocurrency market is growing. For example, market capitalization of bitcoin exceeded 500 trillion won. Accordingly, many studies have been conducted to predict the price of cryptocurrency, and most of them have similar methodology of predicting stock prices. However, unlike stock price predictions, machine learning become best model in cryptocurrency price predictions, conceptually cryptocurrency has no passive income from ownership, and statistically, cryptocurrency has at least three times higher liquidity than stocks. Thats why we argue that a methodology different from stock price prediction should be applied to cryptocurrency price prediction studies. We propose Reverse Walk-forward Validation (RWFV), which modifies Walk-forward Validation (WFV). Unlike WFV, RWFV measures accuracy for Validation by pinning the Validation dataset directly in front of the Test dataset in time series, and gradually increasing the size of the Training dataset in front of it in time series. Train data were cut according to the size of the Train dataset with the highest accuracy among all measured Validation accuracy, and then combined with Validation data to measure the accuracy of the Test data. Logistic regression analysis and Support Vector Machine (SVM) were used as the analysis model, and various algorithms and parameters such as L1, L2, rbf, and poly were applied for the reliability of our proposed RWFV. As a result, it was confirmed that all analysis models showed improved accuracy compared to existing studies, and on average, the accuracy increased by 1.23%p. This is a significant improvement in accuracy, given that most of the accuracy of cryptocurrency price prediction remains between 50% and 60% through previous studies.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.2
• /
• pp.147-160
• /
• 2023

Unlike other currencies, cryptocurrency is not a currency used for general transactions, but is currently applied to various investment assets and its scope is expanding. The purpose of this study is to the effect of personal characteristics on investment intention. As a theoretical background, it was verified by applying the Extended Technical Acceptance Model (ETAM). self-confidence propensity, bandwagon propensity, risk tolerance propensity, network externality, attitude, and Investment intention were composed of variables. The research method collected data from 871 people who had experience in cryptocurrency investment through a survey and analyzed it after excluding the data of 71 people who were judged to be inappropriate. The structural equation modeling method using AMOS was used. As a result of this paper, five hypotheses were accepted as statistically significant. This study concluded that self-confidence propensity, bandwagon propensity, risk tolerance propensity, network externality, and attitude had statistically significant effects on Investment intention. In this respect, this study will be able to provide useful information for cryptocurrency research.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.9
• /
• pp.141-156
• /
• 2018

The purpose of this study is how personal information violation risks affect the intention to use domestic cryptocurrency services. VAM(Value based Adoption Model) model is validated as a theoretical background, selecting perceived ease of use, perceived usefulness and perceived security as a benefit factors, and considers perceived cost, technical complexity, and risk of personal information violation risks as sacrifice factors. The method of this study used questionnaire survey to collect 150 data on user's perception on cryptocurrency services, and also performed a structural equation modeling method using by AMOS 23. The result of this paper shows that all hypotheses are accepted statistically significant except 2 hypothesis. This research is concluded that perceived value is affected on statistically positive impact on perceived ease of use, perceived usefulness and perceived security, and negative impact on risk of personal information violation risk, not statistically perceived fee and technical complexity.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.2
• /
• pp.67-74
• /
• 2019

Since the announcement of bitcoin, new cryptocurrencies have been launched steadily and blockchain technology is also evolving with cryptocurrcies. In particular, security-related technologies such as consensus algorithm and hash algorithm have been improved and transaction processing speed has also been drastically improved to a level that can replace a centralized system. In addition, the advent of smart contract technology and the DApp platform also provides a means for cryptocurrency to decentralize social services beyond just payment. In this paper, we first describe the technologies for implementing cryptocurrency. And the major cryptocurrencies are described with a focus on the technical characteristics. In addition, the development of cryptocurrency technology is expanding the scope of use, so we tried to introduce various cryptocurrencies.

• International journal of advanced smart convergence
• /
• v.12 no.3
• /
• pp.40-50
• /
• 2023

Blockchain is a technology designed to prevent tampering with digital documents or information, safeguarding transaction data and managing it in a structured manner. This proves beneficial in addressing issues of trust and data protection in B2B, B2C, and C2B transactions. Blockchain finds utility not only in financial transactions but also across diverse industrial sectors. This study outlines significant cases and responses that jeopardize the security of blockchain networks and cryptocurrency technology. Additionally, it analyzes safety and risk factors related to blockchain and proposes effective testing methods to preemptively counter these challenges. Furthermore, this study presents key security evaluation metrics for blockchain to ensure a balanced assessment. Additionally, it provides evaluation methods and various test case models for validating the security of blockchain and cryptocurrency transaction services, making them easily applicable to the testing process.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.2
• /
• pp.231-239
• /
• 2020

Cryptocurrency, represented by Bitcoin, initially received little public attention, but recently raised global cryptocurrency investments with recognition of future value. The academic interest in cryptocurrency lies elsewhere. This is because the future value of cryptocurrency is likely to be highly applicable to the technology underlying cryptocurrency. The technology is the blockchain. The purpose of this study is to find out what factors influence logistics companies to adopt blockchain technology. Based on the TOE frame, this study presented expected profit, organizational readiness, technology compatibility, and competitive pressure as factors of adoption of blockchain technology. And the effects of these factors on the adoption intention of logistics companies were analyzed empirically. A survey was conducted on Korean logistics companies. Analysis of the collected data showed that expected profit, organizational readiness, technology compatibility, and competitive pressures influence the intention to adopt blockchain technology. Among them, however, expected profit and organizational readiness were found to have the greatest influence on adoption intention.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.4
• /
• pp.637-659
• /
• 2021

Since the creation of the first Bitcoin blockchain in 2009, the number of cryptocurrency users has steadily increased. However, the number of hacking attacks targeting assets stored in these users' cryptocurrency wallets is also increasing. Therefore, we evaluate the security of the wallets currently on the market to ensure that they are safe. We first conduct threat modeling to identify threats to cryptocurrency wallets and identify the security requirements. Second, based on the derived security requirements, we utilize attack trees and Bayesian network analysis to quantitatively measure the risks inherent in each wallet and compare them. According to the results, the average total risk in software wallets is 1.22 times greater than that in hardware wallets. In the comparison of different hardware wallets, we found that the total risk inherent to the Trezor One wallet, which has a general-purpose MCU, is 1.11 times greater than that of the Ledger Nano S wallet, which has a secure element. However, use of a secure element in a cryptocurrency wallet has been shown to be less effective at reducing risks.

• Convergence Security Journal
• /
• v.22 no.1
• /
• pp.121-127
• /
• 2022

Recently, social issues related to cryptocurrency mining are continuously occurring at the same time as cryptocurrency prices are rapidly increasing. In particular, since cryptocurrency can be acquired through cryptographic operation, anyone with a computer can easily try mining, and as the asset value of major cryptocurrencies such as Bitcoin and Ethereum in creases, public interest is increasing. In addition, the number of cases where individuals who own high-spec computers mine cryptocurrencies in various places such as homes and businesses are increasing. Some miners are mining at companies or public places, not at home, due to the heat problem of computers that consume a lot of electrical energy, causing various problems in companies as well as personal moral problems. Therefore, this study studies the technology to obtain evidence for the traces of mining attempts using the Windows artifacts of the computers that mined cryptocurrency. Through this, it is expected that it can be used for internal audit to strengthen corporate security.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.152-159
• /
• 2023

This study endeavors to enrich investment prospects in cryptocurrency by establishing a rationale for investment decisions. The primary objective involves evaluating the predictability of four prominent cryptocurrencies - Bitcoin, Ethereum, Litecoin, and EOS - and scrutinizing the efficacy of trading strategies developed based on the prediction model. To identify the most effective prediction model for each cryptocurrency annually, we employed three methodologies - AutoRegressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), and Prophet - representing traditional statistics and artificial intelligence. These methods were applied across diverse periods and time intervals. The result suggested that Prophet trained on the previous 28 days' price history at 15-minute intervals generally yielded the highest performance. The results were validated through a random selection of 100 days (20 target dates per year) spanning from January 1st, 2018, to December 31st, 2022. The trading strategies were formulated based on the optimal-performing prediction model, grounded in the simple principle of assigning greater weight to more predictable assets. When the forecasting model indicates an upward trend, it is recommended to acquire the cryptocurrency with the investment amount determined by its performance. Experimental results consistently demonstrated that the proposed trading strategy yields higher returns compared to an equal portfolio employing a buy-and-hold strategy. The cryptocurrency trading model introduced in this paper carries two significant implications. Firstly, it facilitates the evolution of cryptocurrencies from speculative assets to investment instruments. Secondly, it plays a crucial role in advancing deep learning-based investment strategies by providing sound evidence for portfolio allocation. This addresses the black box issue, a notable weakness in deep learning, offering increased transparency to the model.