• Journal of the Korean Data and Information Science Society
• /
• v.28 no.2
• /
• pp.251-260
• /
• 2017

The option pricing of Black와 Scholes (1973) and Merton (1973) has been widely reported to fail to reflect the time varying volatility of financial time series in many real applications. For example, Duan (1995) proposed GARCH option pricing method through Monte Carlo simulation. However, financial time series is known to follow a fat-tailed and leptokurtic probability distribution, which is not explained by Duan (1995). In this paper, in order to overcome such defects, we proposed the option pricing method based on GARCH models with normal mixture errors. According to the analysis of KOSPI200 option price data, the option pricing based on GARCH models with normal mixture errors outperformed the option pricing based on GARCH models with normal errors in the unstable period with high volatility.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.730-736
• /
• 2011

In this paper, we designed the models for pattern classification which can reflect the latest trend in time series. It has been shown that fusion models based on statistical and AI methods are superior to traditional ones for the pattern classification model supporting decision making. Especially, the hit rates of pattern classification models combined with fuzzy theory are relatively increased. The statistical SVM models combined with fuzzy membership function, or the models combining neural network and FCM has shown good performance. BPN, PNN, FNN, FCM, SVM, FSVM, Decision Tree, Time Series Analysis, and Regression Analysis were used for pattern classification models in the experiments of this paper. The economical indices DB with time series properties of the financial market(Korea, KOSPI200 DB) and the electrocardiogram DB of arrhythmia patients in hospital emergencies(USA, MIT-BIH DB) were used for data base.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.7
• /
• pp.3053-3061
• /
• 2011

This study examines the relationship between R&D(research & development) investment and market value among KOSDAQ firms in the Korea Stock Exchange. We investigate the effect of R&D investment on firm value in both total sample and sub-samples classified by firm characteristics based on types of firms. And we study the impact of a major economic disruption as the global financial crisis triggered by sub-prime mortgage problem in the US on R&D investment relative to the firm value. We find that R&D investment positively affects firm value and the squared term of R&D investment is found to be significant and negatively correlated with market value. This suggests the presence of nonlinear relationship like a reverse U-shape between R&D investment and market value in total sample and most of sub-samples. And we find firm characteristics and global financial crisis partially affect the contribution of R&D investment to market value in some of sub-samples.

• Korea Real Estate Review
• /
• v.27 no.1
• /
• pp.7-16
• /
• 2017

In this study, we examine whether there are prospect theory investment patterns for individual investors in the real estate market. We use the maximum potential profit rate and the maximum potential loss rate of individual investors as a research method and additionally analyze it using the Jeong and Park(2015) model. As a result of the analysis, it was found that the investment pattern according to the prospect theory and disposition effect for individual investors. And we find the difference between zoning areas. This difference in investment behavior is believed to be due to the purpose of the real estate and the existence of rent fee, which creates a difference in investment behavior depending on the purpose. The limitations of this study are the analysis measurement of potential profit and potential loss using the land price index like the study of jeong and Park(2015). This implies that a new property price index needs to be developed or a benchmark for real estate assets is needed for deeper study of real estate investment sentiment.

• Journal of the Korea Convergence Society
• /
• v.13 no.4
• /
• pp.17-24
• /
• 2022

Bitcoin is a peer-to-peer cryptocurrency designed for electronic transactions that do not depend on the government or financial institutions. Since Bitcoin was first issued, a huge blockchain financial market has been created, and as a result, research to predict Bitcoin price data using machine learning has been increasing. However, the inefficient Hyper-parameter optimization process of machine learning research is interrupting the progress of the research. In this paper, we analyzes and presents the direction of Hyper-parameter optimization through experiments that compose the entire combination of the Timesteps, the number of LSTM units, and the Dropout ratio among the most representative Hyper-parameter and measure the predictive performance for each combination based on Bitcoin price prediction model using LSTM layer.

• Journal of the Society of Disaster Information
• /
• v.17 no.2
• /
• pp.375-390
• /
• 2021

Purpose: Most of cybersecurity breaches occur in SMEs. As the existing cybersecurity framework and certification system are mainly focused on financial and large companies, it is difficult for SMEs to utilize it due to lack of cybersecurity budget and manpower. So it is necessary to come up with measures to allow SMEs to voluntarily manage cyber risks. Method: After reviewing Cybersecurity market, cybersecurity items of financial institutions, cybersecurity framework comparison and cybersecurity incidents reported in the media, the criticality of cybersecurity items was analyzed through AHP analysis. And cybersecurity items of non-life insurers were also investigated and made a comparison between them. Result: Cyber risk management methods for SMEs were proposed for 20 major causes of cyber accidents. Conclusion: We hope that the cybersecurity risk assessment measures of SMEs in Korea will help them assess their risks when they sign up for cyber insurance, and that cyber risk assessment also needs to be linked to ERM standardization.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.171-178
• /
• 2022

In this paper, we propose a classification method according to the type and characteristics of stablecoins for risk analysis, and analyze the risk factors of each stablecoin based on this classification. First, this paper explains the technologies and ecosystem of blockchain and decentralized finance(DeFi) to understand stablecoins. In addition, the operation principle of the major stablecoins currently released and used is explained for each proposed classification type. Based on this, the risk type and risk factors of each stablecoin are derived. The risk types proposed in this paper are classified as defegging, liquidation, and exploit, and the risk factors are classified as depegging due to reliability of operator, depegging due to reliability of algorithm, depegging due to failure of algorithm, liquidation due to high volatilty and oracle attack. Based on the proposed classification, we analyze the risk factors of major stablecoins currently circulating in the crypto market.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.67-75
• /
• 2023

Stock price prediction is an important topic extensively discussed in the financial market, but it is considered a challenging subject due to numerous factors that can influence it. In this research, performance was compared and analyzed by applying time series prediction models (LSTM, GRU) and non-time series prediction models (RF, SVR, KNN, LGBM) that do not take into account the temporal dependence of data into stock price prediction. In addition, various data such as stock price data, technical indicators, financial statements indicators, buy sell indicators, short selling, and foreign indicators were combined to find optimal predictors and analyze major factors affecting stock price prediction by industry. Through the hyperparameter optimization process, the process of improving the prediction performance for each algorithm was also conducted to analyze the factors affecting the performance. As a result of feature selection and hyperparameter optimization, it was found that the forecast accuracy of the time series prediction algorithm GRU and LSTM+GRU was the highest.

• Journal of Industrial Convergence
• /
• v.20 no.2
• /
• pp.11-19
• /
• 2022

This study examines the role of economic uncertainty in stock price determination in the domestic stock market. To this end, we analyzed the relationship between economic uncertainty indices at home and abroad (USA, China) and stock returns for non-financial companies in Korea from January 2000 to 2017. For the analysis model, the 3-factor model of Fama and French (1992) and the 5-factor model including momentum and liquidity were used. As a result of the analysis, a portfolio with a high beta of economic uncertainty showed higher stock returns than a portfolio with a low beta. This was the same as the US analysis result. Also, the analysis results using the US uncertainty index were more significant than the regression analysis results using the Korean economic uncertainty index.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.55-66
• /
• 2023

This study analyzes the characteristics of customer's preferences on banking channels (branches, automated machines, telebanking, internet banking, and mobile banking) and examines the factors influencing channel usage. To accomplish this, ANOVA and multiple regression analysis are performed using customer data from Bank A. The analysis reveals that customers primarily utilizing branch counter transactions have a significant impact on the profitability of 1st and 2nd grade banks, particularly among the age group of 50 years and above. Additionally, it is observed that as customers' loan, deposit, and financial product holdings increase, branch counter transactions also increase. On the other hand, it is found that as the usage of mobile banking decreases in terms of loans and deposits, transaction volume increases.