• The Korean Journal of Applied Statistics
• /
• v.36 no.2
• /
• pp.141-166
• /
• 2023

This paper investigates synthetic data generation methods and their evaluation measures. There have been increasing demands for releasing various types of data to the public for different purposes. At the same time, there are also unavoidable concerns about leaking critical or sensitive information. Many synthetic data generation methods have been proposed over the years in order to address these concerns and implemented in some countries, including Korea. The current study aims to introduce and compare three representative synthetic data generation approaches: Sequential regression, nonparametric Bayesian multiple imputations, and deep generative models. Several evaluation metrics that measure the utility and disclosure risk of synthetic data are also reviewed. We provide empirical comparisons of the three synthetic data generation approaches with respect to various evaluation measures. The findings of this work will help practitioners to have a better understanding of the advantages and disadvantages of those synthetic data methods.

• The Journal of shipping and logistics
• /
• v.27 no.3
• /
• pp.457-474
• /
• 2011

The aim of this study is to analyze the efficiency of major ports in Northeast Asia such as Korea, China and Japan. For the empirical analysis, we tried to apply the data envelopment analysis (DEA), which is an efficiency evaluation model based on mathematical programming theory, and we also established a model to Northeast Asian ports. In our opinion, DEA analysis which involves multiple inputs as well as multiple outputs in its efficiency valuation makes analysis more suitable for port efficiency measurement because ports produce a number of different outputs. In this paper, we attempted to analyze the relative efficiency of 27 ports (5 Korean ports, 13 Chinese ports, 9 Japanese ports) through DEA-CCR, DEA-BCC models. According to the result, Chinese ports are relatively efficient than Korean and Japanese ports. The result of the analysis shows that 7 Chinese ports are efficient in DEA-CCR model in 2009, but in DEA-BCC model 8 Chinese ports and 1 Koran port are efficient. Most of inefficient ports have a value closed to 1 in efficiency for scale, it means that the reason of inefficiency is caused from the technical aspect. Furthermore, we also verified that there exists excess of input in Korean and Japanese ports than Chinese ports.

• Journal of the Korean Geotechnical Society
• /
• v.23 no.7
• /
• pp.17-25
• /
• 2007

Various geotechnical problems due to insufficient bearing capacity or excessive settlement are likely to occur when constructing roads or large complexes on soft ground. Accurate predictions of the magnitude of settlement and the consolidation time provide numerous options of ground improvement methods and, thus, enable to save time and expense of the whole project. Asaoka's method is probably the most frequently used one for settlement prediction and the empirical formulae such as Hyperbolic method and Hoshino's method are also often used. To find an elaborate method of predicting the embankment settlement, two recurrent type neural network models, such as Jordan model and Elman-Jordan model, are adopted. The data sets of settlement measured at several domestic sites are analyzed to obtain the most suitable model structures. It was shown from the comparison between predicted and measured settlements that Jordan model provides better predictions than Elman-Jordan model does and that the predictions using CPT results are more accurate than those using SPT results. It is believed that RNN using cone penetration test results can be a highly efficient tool in predicting settlements if enough field data can be obtained.

• Journal of Digital Convergence
• /
• v.20 no.1
• /
• pp.33-39
• /
• 2022

This study aims to investigate the online class preference depending on students' gender and school level. To achieve this aim, the study conducted a survey on 4,803 elementary, middle, and high school students in 17 regions nationwide. The valid data of 4,524 were then analyzed using the Apriori algorithm to discern the associated patterns of the online class preference corresponding to their gender and school level. As a result, a total of 16 rules, including 7 from elementary school students, 4 from middle school students, and 5 from high school students were derived. To be specific, elementary school male students preferred software-based classes whereas elementary female students preferred maker-based classes. In the case of middle school, both male and female students preferred virtual experience-based classes. On the other hand, high school students had a higher preference for subject-specific lecture-based classes. The study findings can serve as empirical evidence for explaining the needs of online classes perceived by K-12 students. In addition, this study can be used as basic research to present and suggest areas of improvement for diversifying online classes. Future studies can further conduct in-depth analysis on the development of various online class activities and models, the design of online class platforms, and the female students' career motivation in the field of science and technology.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.341-348
• /
• 2022

This study analyzed the accounting conservatism of companies listed on KONEX. The analysis of the existing accounting conservatism presents the analysis results for the KOSPI market or the KOSDAQ market. However, in July 2013, Korea opened a new publicly traded market called KONEX, which has been continuously operated to increase the possibility of SMEs' financing. However, research on KONEX has not been conducted relatively actively, and the current prior research is also focused on earnings management. This study differs from previous studies in that it analyzes accounting conservatism, which is one of the accounting policies. For this purpose, the period from 2014 to 2020 was set as the analysis period, and empirical analysis was conducted using the asymmetric timeliness models, Ball and Shivakumar (2005) and Basu (1997). As a result of the analysis, conditional conservatism was also confirmed in the KONEX market. That is, it was confirmed that the timeliness of the bad news was higher than the good news. Second, no significant difference was found in the results of analyzing whether there is a difference in the conservatism of KONEX companies according to the size of the auditor. In other words, it was confirmed that the size of the auditor in the KONEX market is not a significant variable. This study expanded the existing research in that it analyzed accounting policies targeting the KONEX market.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.129-148
• /
• 2023

Bitcoin is a blockchain technology-based digital currency that has been recognized as a representative cryptocurrency and a financial investment asset. Due to its highly volatile nature, Bitcoin has gained a lot of attention from investors and the public. Based on this popularity, numerous studies have been conducted on price and trend prediction using machine learning and deep learning. This study employed LSTM (Long Short Term Memory) and CNN (Convolutional Neural Networks), which have shown potential for predictive performance in the finance domain, to enhance the classification accuracy in Bitcoin price trend prediction. XAI(eXplainable Artificial Intelligence) techniques were applied to the predictive model to enhance its explainability and interpretability by providing a comprehensive explanation of the model. In the empirical experiment, CNN was applied to technical indicators and Google trend data to build a Bitcoin price trend prediction model, and the CNN model using both technical indicators and Google trend data clearly outperformed the other models using neural networks, SVM, and LSTM. Then SHAP(Shapley Additive exPlanations) was applied to the predictive model to obtain explanations about the output values. Important prediction drivers in input variables were extracted through global interpretation, and the interpretation of the predictive model's decision process for each instance was suggested through local interpretation. The results show that our proposed research framework demonstrates both improved classification accuracy and explainability by using CNN, Google trend data, and SHAP.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.267-283
• /
• 2023

The COVID-19 pandemic, which began in December 2019 and continues to this day, has left the public needing information to help them cope with the pandemic. However, COVID-19-related fake news on social media seriously threatens the public's health. In particular, if fake news related to COVID-19 is massively spread with similar content, the time required for verification to determine whether it is genuine or fake will be prolonged, posing a severe threat to our society. In response, academics have been actively researching intelligent models that can quickly detect COVID-19-related fake news. Still, the data used in most of the existing studies are in English, and studies on Korean fake news detection are scarce. In this study, we collect data on COVID-19-related fake news written in Korean that is spread on social media and propose an intelligent fake news detection model using it. The proposed model utilizes the frequency information of parts of speech, one of the linguistic characteristics, to improve the prediction performance of the fake news detection model based on Doc2Vec, a document embedding technique mainly used in prior studies. The empirical analysis shows that the proposed model can more accurately identify Korean COVID-19-related fake news by increasing the recall and F1 score compared to the comparison model.

• Asia Marketing Journal
• /
• v.15 no.3
• /
• pp.53-77
• /
• 2013

As advertising and promotions are categorized as operating expenses, managers tend to reduce marketing budget to improve their short term profitability. Gauging the value and accountability of marketing spending is therefore considered as a major research priority in marketing. To respond this call, recent studies have documented that financial market reacts positively to a firm's marketing activity or marketing related outcomes such as brand equity and customer satisfaction. However, prior studies focus on the relation of marketing variable and financial market variables. This study suggests a channel about how marketing activity increases firm valuation. Specifically, we propose that a firm's marketing activity increases the level of the firm's product market information and thereby the dispersion in financial analysts' earnings forecasts decreases. With less uncertainty about the firm's future prospect, the firm's managers and shareholders have less information asymmetry, which reduces the firm's cost of capital and thereby increases the valuation of the firm. To our knowledge, this is the first paper to examine how informational benefits can mediate the effect of marketing activity on firm value. To test whether marketing activity contributes to increase in firm value by mitigating information asymmetry, this study employs a longitudinal data which contains 12,824 firm-year observations with 2,337 distinct firms from 1981 to 2006. Firm value is measured by Tobin's Q and one-year-ahead buy-and-hold abnormal return (BHAR). Following prior literature, dispersion in analysts' earnings forecasts is used as a proxy for the information gap between management and shareholders. For model specification, to identify mediating effect, the three-step regression approach is adopted. All models are estimated using Markov chain Monte Carlo (MCMC) methods to test the statistical significance of the mediating effect. The analysis shows that marketing intensity has a significant negative relationship with dispersion in analysts' earnings forecasts. After including the mediator variable about analyst dispersion, the effect of marketing intensity on firm value drops from 1.199 (p < .01) to 1.130 (p < .01) in Tobin's Q model and the same effect drops from .192 (p < .01) to .188 (p < .01) in BHAR model. The results suggest that analysts' forecast dispersion partially accounts for the positive effect of marketing on firm valuation. Additionally, the same analysis was conducted with an alternative dependent variable (forecast accuracy) and a marketing metric (advertising intensity). The analysis supports the robustness of the main results. In sum, the results provide empirical evidence that marketing activity can increase shareholder value by mitigating problem of information asymmetry in the capital market. The findings have important implications for managers. First, managers should be cognizant of the role of marketing activity in providing information to the financial market as well as to the consumer market. Thus, managers should take into account investors' reaction when they design marketing communication messages for reducing the cost of capital. Second, this study shows a channel on how marketing creates shareholder value and highlights the accountability of marketing. In addition to the direct impact of marketing on firm value, an indirect channel by reducing information asymmetry should be considered. Potentially, marketing managers can justify their spending from the perspective of increasing long-term shareholder value.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.83-90
• /
• 2023

The recent trend in younger generations of wearing traditional costumes or incorporating fusion hanbok into daily wear necessitates the development of modern hair accessories to complement hanbok. The purpose of this study is to develop practical and modern hair accessory designs inspired by royal women's hair ornaments that complement hanbok, and therefore expand the scope of fashion content development utilizing hanbok culture as well as meeting the demand for various experiences of traditional culture. This research studied the literature on traditional hairstyles and accessories of Queen Yeong and constructed models of these accessories for the purpose of empirical research. The production process first required creating a basic foundation of nylon mesh reflecting the silhouette of a traditional hairstyle, and then grafting a digital textile printed fabric using majestic and extravagant royal relics on top, thus employing the trompe l'oeil technique to ultimately give the impression of wearing traditional jewelry. As a result, a total of six hair accessory designs were completed, produced with hairbands, hair pins, and hair ties. In addition, the accessories are designed to be easily worn regardless of the wearer's hair style, and the stiff yet flexible nylon mesh effectively expresses the shape of a voluminous hairstyle and creates an optical illusion, blending into the hair. These research results present a unique aesthetic and cultural experience to the greater public seeking both daily entertainment and value from rarity.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.18 no.1
• /
• pp.237-251
• /
• 2023

This study tried to understand the effect of internal resources, capabilities, and business model innovation of venture enterprises on industrial property performance, as based on previous studies that securing industrial property rights has a positive effect on the technology commercialization of venture companies. Venture company capabilities were classified into intrinsic elements of a company (company's research resources) and creative elements (commercialization capabilities) that implement them, and they were intended to show that they could lead to a company's potential competitiveness through innovation in business models. In order to verify this research purpose, an empirical analysis was conducted on 1,733 corporate companies among venture confirmation companies subject to the 2019 venture company precision survey. It was confirmed that the systematic research organization and commercialization capabilities of venture companies were significant (+) in industrial property performance. However, in the final research model that applied both the rules of the business model's innovation variable, commercialization capability and business model innovation were significant (-), and research organization × business model innovation showed significant results (+). This means that venture companies' excellent resources and capabilities can have a positive impact on industrial property performance individually, but when applying the level of innovation in the actual business model, they must interact with the business model. The results of this study are meaningful in that it is necessary to pursue business model innovation that secures clear differentiators compared to competitors as well as strengthening the company's internal resources and capabilities to secure industrial assets and innovation growth.