• Journal of Distribution Science
• /
• v.14 no.10
• /
• pp.109-116
• /
• 2016

Purpose - This study investigates the purchase pattern relating to soybean products in Korea. Specifically, the effect of branding based on a regional name was analyzed in terms of consumer purchase frequencies. The primary purpose of this study is to understand why family characteristics affect product selection for a regional brand in the soybean food category. Research design, data, and methodology - We used data collected by the Rural Development Administration (RDA) of Korea. The RDA has monitored agricultural food consumers for years in order to obtain purchase records. Panel participants live in regions near the capital city of Seoul, Korea. Examining data from January 2010 to May 2016, 667 families were selected for analysis. The final data set was 1,335,402. Each purchase item by each individual family was aggregated to a countable weekly observation. To analyze the data set quantitatively, zero-inflation regression was adopted, which was appropriate to avoid biases from overly dispersed observations. Results - We hypothesized the effects of regional branding from the viewpoint of the family characteristics. The first hypothesis was that the number of children would be positively associated with the purchase of a regional brand of soybean products. The result strongly supported this hypothesis. The second hypothesis was that the number of family members would be negatively associated with the purchase of the soybean products of a regional brand. Based on empirical analysis, we concluded that this hypothesis was partially supported. The third hypothesis was the presence of an interaction effect between the number of children and the family size, which was supported by the results. As a supplementary analysis, we also tested mean-variance differences in terms of categories and regional branding with corporate branding. Conclusion - The results of this study provide insights for regional branding strategies in agricultural food management. This study appears to be one of the seminal studies trying to analyze purchase patterns from longitudinal observations. In addition, this study adopted variables characterizing family lifestyle. This study confirmed that children and family size should be considered when soybean product brands are introduced.

• Management & Information Systems Review
• /
• v.32 no.4
• /
• pp.103-126
• /
• 2013

Growing serious on the required conditions for the On-the-Job Education Training at the firm field, a large number of firm make a plan for implementation and pushing ahead of the On-the-Job Education Training. Further, A lot of firms effort to attract multi-professional person at an firm level recently. However, there were little information about the what for the reason to choose the OJET, come what may on the OJET and how to thinking on the outcome for the latent employee. On the basis of these issues, this study discovered the motivations from the employee point, finding out the factors on the effect of the choice as the OJET type and the integration point of view. The study results found out significant variables of the OJET type factor, the business for which one is responsible factor, OJET participation reason factor, business environment factor and individual background factor on the OJET decision plan. On the basis of the results, this article further discusses what we need to do for the intensity of participation invigoration at a firm level.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.15 no.2
• /
• pp.86-96
• /
• 2003

A fracture or breakage of the concrete armor units in the primary cover layer of breakwaters is studied by using the reliability analysis which may be defined as the structural stability. The reliability function can be derived as a function of the angle of rotation that represents the rocking of armor units quantitatively. The relative influences of all of random variables related to the material and geometric properties on the fracture of armor units is analyzed in detail. In addition, the probability of failure for the fracture of individual armor unit can be evaluated as a function of the incident wave height. Finally, Bernoulli random process and the allowable fracture ratio may be introduced together in this paper, by which the probability of failure of a breakwater due to the fracture of armer units can be obtained straightforwardly. It is found that the probability of failure of a breakwater due to the fracture of armor units may be varied with the several allowable fracture ratios. Therefore, it should be necessary to consider the structural stability as well as the hydraulic stability for the design of breakwaters with multi-leg slender concrete armor units of large size under wave action in deep water.

• Korean Journal of Social Welfare
• /
• v.57 no.4
• /
• pp.275-290
• /
• 2005

This study investigates whether previous experiences in the labor market such as previous employment type and job type are related to the economic status and poverty in the elderly in Korea. Previous studies are limited in explaining the causes of poverty by using only the proxy variables such as age, marital status, and gender to classify the poverty status of the elderly after poverty has been identified. Therefore little is known about how the economic well-being after retirement is interrelated with previous job experiences in the labour market. The results indicate that the last job type and type of employment are significant predictors for the economic status of elderly. Job type in the labour market is critical for the lifetime economic status of an individual. These findings imply that we might need to reconsider the current public pension system which directly relates the benefit level to the amount of contribution. A system introducing a basic pension or a minimum pension benefit based on the citizenship or residence might be an alternative worth to consider.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.187-194
• /
• 2019

Traditional demand forecasting methods are difficult to meet the needs of companies due to rapid changes in the market and the diversification of individual consumer needs. In a diversified production environment, the right demand forecast is an important factor for smooth yield management. Many of the existing predictive models commonly used in industry today are limited in function by little. The proposed model is designed to overcome these limitations, taking into account the part where each model performs better individually. In this paper, variables are extracted through Gray Relational analysis suitable for dynamic process analysis, and statistically predicted data is generated that includes characteristics of historical demand data produced through ARIMA forecasts. In combination with the LSTM model, demand forecasts can then be calculated by reflecting the many factors that affect demand forecast through an architecture that is structured to avoid the long-term dependency problems that the neural network model has.

• Journal of the Korean Society of Radiology
• /
• v.13 no.4
• /
• pp.547-555
• /
• 2019

The purpose of this study was to evaluate the usefulness of routine liver ultrasonography on the basis of the scoring system according to the morphological parameters of liver ultrasound images and the histopathological results of liver biopsy. The morphological parameters of the liver through ultrasonography were divided into liver surface, liver edge and liver parenchyma. Pathologic results of liver biopsy were classified as mild fibrosis(F1), significant fibrosis(F2), severe fibrosis(F3), and cirrhosis(F4). In conclusion, routine ultrasound examination showed a sensitive predictive factor for fibrosis with mild fibrosis (F1) to severe fibrosis (F3) were liver edge>liver parenchyma>liver surface. However, the predictive factors for detecting cirrhosis (F4) were liver parenchyma>liver surface>liver edge. The use of three variable combinations rather than individual variables in routine ultrasonography may be useful in evaluating the degree and progress of liver fibrosis.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.1
• /
• pp.123-130
• /
• 2021

With the recent developments in computer technology, there has been an increasing interest in the field of machine learning. This also has led to a significant increase in real business cases of machine learning theory in various sectors. In finance, it has been a major challenge to predict the future value of financial products. Since the 1980s, the finance industry has relied on technical and fundamental analysis for this prediction. For future value prediction models using machine learning, model design is of paramount importance to respond to market variables. Therefore, this paper quantitatively predicts the stock price movements of individual stocks listed on the KOSPI market using machine learning techniques; specifically, the reinforcement learning model. The DQN and A2C algorithms proposed by Google Deep Mind in 2013 are used for the reinforcement learning and they are applied to the stock trading strategies. In addition, through experiments, an input value to increase the cumulative profit is selected and its superiority is verified by comparison with comparative algorithms.

• Journal of Digital Convergence
• /
• v.19 no.2
• /
• pp.169-174
• /
• 2021

While the importance of information security policies is heightened, numerous empirical studies have been conducted to investigate the factors that influence employee's willingness to comply organizational security policies. Some of those studies, however, were not consistent and even contradictory each other. Synthesizing research outcomes has been resulted as qualitative literature reviews or quantitative analysis on individual effect sizes, which leads to meta-analyze on whole research model. This study investigated 28 empirical research based on the deterrence theory with sanction certainty, severity and celerity. The analysis with random effect model resulted in well-fitted research model as well as all of significant paths in the model. Future research can include informal deterrent factors and contextual factors as moderator variables.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.147-170
• /
• 2022

Although the number of patent which is one of the core outputs of technological innovation continues to increase, the number of low-value patents also hugely increased. Therefore, efficient evaluation of patents has become important. Estimation of patent lifespan which represents private value of a patent, has been studied for a long time, but in most cases it relied on a linear model. Even if machine learning methods were used, interpretation or explanation of the relationship between explanatory variables and patent lifespan was insufficient. In this study, patent lifespan (number of renewals) is predicted based on the idea that patent lifespan represents the value of the patent. For the research, 4,033,414 patents applied between 1996 and 2017 and finally granted were collected from USPTO (US Patent and Trademark Office). To predict the patent lifespan, we use variables that can reflect the characteristics of the patent, the patent owner's characteristics, and the inventor's characteristics. We build four different models (Ridge Regression, Random Forest, Feed Forward Neural Network, Gradient Boosting Models) and perform hyperparameter tuning through 5-fold Cross Validation. Then, the performance of the generated models are evaluated, and the relative importance of predictors is also presented. In addition, based on the Gradient Boosting Model which have excellent performance, Accumulated Local Effects Plot is presented to visualize the relationship between predictors and patent lifespan. Finally, we apply Kernal SHAP (SHapley Additive exPlanations) to present the evaluation reason of individual patents, and discuss applicability to the patent evaluation system. This study has academic significance in that it cumulatively contributes to the existing patent life estimation research and supplements the limitations of existing patent life estimation studies based on linearity. It is academically meaningful that this study contributes cumulatively to the existing studies which estimate patent lifespan, and that it supplements the limitations of linear models. Also, it is practically meaningful to suggest a method for deriving the evaluation basis for individual patent value and examine the applicability to patent evaluation systems.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.17 no.3
• /
• pp.51-76
• /
• 2022

Identifying the factors that influence the formation of the entrepreneurial intention is important in cultivating entrepreneurs and inducing entrepreneurial innovation in the country. Previous studies have mainly examined the direct effects of social cognition attributes as predictors on entrepreneurial intentions or entrepreneurial activities. However, the fundamental factors that these social cognition attributes are derived from have not been sufficiently addressed in the field of entrepreneurship. Based on social cognitive theory and schema theory, this study assumes that an individual's entrepreneurial experience is an important antecedent factor in forming social cognitive attributes, and reveals the mechanism for how experience forms entrepreneurial intention. To this end, this study analyzes the influence of entrepreneurs' prior experience of entrepreneurial activities on entrepreneurial self-efficacy, opportunity recognition, and fear of failure which are considered to be the main variables that shape entrepreneurial intention. And it analyzes how these factors have a significant effect on entrepreneurship intention. Along with this, the mediating role of these social cognitive attributes is analyzed in order to understand the path that leads from entrepreneurial experience to entrepreneurial intention. This study also suggests how gender moderates the effect of entrepreneurship experience on social cognitive attributes. As a result of the analysis, it was found that entrepreneurial experience increase entrepreneurial self-efficacy and opportunity recognition of entrepreneurs, and decrease the fear of failure. These social perception attribute significantly mediate the relationship between entrepreneurial experience and entrepreneurial intention. This study also found that there are significant moderating effects of gender on the relationship of entrepreneurial experience and both of entrepreneurial self-efficacy and fear of failure. This study also analyzed the impact of the entrepreneurial experience of failure, which corresponds to the detailed experience. Similar to the results of entrepreneurial experience analysis, entrepreneurial experience of failure plays a role in enhancing entrepreneurial self-efficacy. However, its effect on opportunity recognition and fear of failure were not significant. An empirical analysis of data related to 25,047 entrepreneurs from 87 countries, using the Global Entrepreneurship Monitor (GEM), shows the differences in the formation of individuals' entrepreneurial intentions according to entrepreneurial experience and the mediating role of social cognitive attributes. The study has embodied the social cognitive theory on entrepreneurial intention by shedding light on the variables that are important but alienated for increasing entrepreneurial intention. Moreover, the study enhances the understanding of cognitive processes leading from individual experiences to entrepreneurial intentions. This study also emphasizes the importance of differentiated approach by gender for boosting entrepreneurial intention through analysis of moderating effect of gender.