• The Journal of Society for e-Business Studies
• /
• v.20 no.3
• /
• pp.89-112
• /
• 2015

Recently, the business environment of healthcare has changed rapidly due to the entering the mobile era, the intensifying global competition, and the explosion of healthcare needs. Despite of necessity in expanding new IT-based medical services and investing IT resources to respond environmental changes, the small and medium sized hospitals could not realize these requirements due to the limited management resources. CHISSMH is designed and presented in this research to provide high valued clouding medical services with reasonable price. CHISMH is designed and presented in this research to provide high valued medical services with reasonable price through cloud computing. CHISME is designed to maximize resource pooling and sharing through the visualization. By doing so, Cloud Service provider could minimize maintenance cost of cloud data center, provide high level services with reasonable pay-per-use price. By doing so, Cloud Service provider could minimize maintenance cost of cloud data center, and could provide high level services with reasonable pay-per-use price. CHISME is expected to be base framework of cloud HIS services and be diffusion factor of cloud HIS services Operational experience in CHISSMH with 15 hospitals is analyzed and presented as well.

• The Journal of Society for e-Business Studies
• /
• v.27 no.2
• /
• pp.153-173
• /
• 2022

This study analyzes yelp's online restaurant reviews written in 2019 and explores the factors influencing the decision of the usefulness for online reviews in the restaurant consumption decision process. Specifically, factors expected to affect review usefulness are classified according to the Elaboration Likelihood model. Also, it is assumed that the price range of the restaurant would have a moderating role. For the analysis, datasets provided by yelp.com in February 2020 are used. Among the datasets, online reviews of businesses located in Nevada in the US and belonging to the Food and Restaurant categories are targeted. As a result of the negative binomial regression analysis, it is confirmed that the central cues including review depth and readability and the peripheral cues including review consistency, reviewer popularity, and reviewer exposure positively affect the review usefulness. It is also confirmed that the influences of antecedents that affect the review restaurant prices moderate the effect of the central and peripheral cues on the review usefulness. It also provides implications for the need for price-differentiated review management strategies by review platforms and restaurant businesses.

• Journal of the Korea Convergence Society
• /
• v.12 no.6
• /
• pp.9-16
• /
• 2021

In the past, there have been various studies on predicting the stock market by machine learning techniques using stock price data and financial big data. As stock index ETFs that can be traded through HTS and MTS are created, research on predicting stock indices has recently attracted attention. In this paper, machine learning models for KOSPI's up and down predictions are implemented separately. These models are optimized through a grid search of their control parameters. In addition, a hybrid machine learning model that combines individual models is proposed to improve the precision and increase the ETF trading return. The performance of the predictiion models is evaluated by the accuracy and the precision that determines the ETF trading return. The accuracy and precision of the hybrid up prediction model are 72.1 % and 63.8 %, and those of the down prediction model are 79.8% and 64.3%. The precision of the hybrid down prediction model is improved by at least 14.3 % and at most 20.5 %. The hybrid up and down prediction models show an ETF trading return of 10.49%, and 25.91%, respectively. Trading inverse×2 and leverage ETF can increase the return by 1.5 to 2 times. Further research on a down prediction machine learning model is expected to increase the rate of return.

• Journal of Digital Convergence
• /
• v.20 no.5
• /
• pp.411-422
• /
• 2022

The purpose of this study was to identify factors that affect the characteristics and intentions of the elderly to use digital wealth management services. The subjects of this study were 312 elderly people over 50 years old. Based on the Value-based Adoption Model(VAM), the research model added price value, social influence, and perceived risk as research variables. As a result of empirical analysis, it was found that usefulness, enjoyment, price value, and social influence all had a significant positive (+) effect on perceived value. It was found that technicality had a significant negative (-) effect. On the other hand, no significant effect relationship was tested on perceived risk. The perceived value had a significant positive (+) effect on the intention to use. This study was meaningful in the academic research that it applied a research model that reflected the characteristics of the elderly who were not treated as mainstream in the technology acceptance model for digital wealth management services. In addition, it provided practical implications for providers' marketing strategies and government/public institution policy establishment to increase the use of digital wealth management services for the elderly.

• Journal of Distribution Research
• /
• v.6 no.2
• /
• pp.19-40
• /
• 2002

According to the secondary data, private brand(PB)'s share of retail sales is 25-30% in the USA, but about 45 in Korea. In Korea PB's average price is 23.3% less than manufacturer brand. It is very interest that PB's price advantage doesn't have a good effect on it's share of retail sales. This research's objective is to study why Korean consumers don't purchase private brand cheaper than manufacturer brand. A theoretical reasoning depends on information cue theory and means-ends model of perceived value. A unit of analysis is consumers who purchase private brand at E-mart in Pusan city, one of largest discount store in Korea. Hypothesis tested by Lisrel's structural equation model and interesting results as follows: First, favorable brand image among extrinsic cues is most positively correlated with perceived quality/sacrifice and intrinsic cues is also statistically significant. This fact imply that intrinsic cues; package, logo, country of origin are very important in the adoption of private brand in Korea. Second, compared with manufacturer's brand, PB's perceived price is positively correlated with perceived quality/sacrifice. This fact imply a assimilation effect between manufacturer's brand and private brand. Finally, a correlation between perceived sacrifice and PB proneness is satistically insignificant, but perceived quality has a significant effect on its proneness. this fact imply that innovators(about 4% of potential consumer) are risk-taker.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.2
• /
• pp.191-196
• /
• 2015

There have been many studies on statistical forecasting on firm's performance and stock price by applying various financial indicators such as debt ratio and sales growth rate. Selecting predictors for constructing a prediction model among the various financial indicators is very important for precise prediction. Most of the previous studies applied variable selection algorithms for selecting predictors. However, the variable selection algorithm is considered to be at risk of eliminating certain amount of information from the indicators that were excluded from model construction. Therefore, we propose a firm's performance prediction model which principal component analysis is applied instead of the variable selection algorithm, in order to reduce dimensionality of input variables of the prediction model. In this study, we constructed the proposed prediction model by using financial data of American IT companies to empirically analyze prediction performance of the model.

• Information Systems Review
• /
• v.7 no.1
• /
• pp.97-113
• /
• 2005

This paper designed and implemented(programmed) a comparative shopping agent that helps consumers to shop at on-line shopping malls over Internet. At offline stores, as consumers usually tell a sales clerk about a manufacturer, functions and price range of an item they want to purchase, the sales clerk will show the products or relevant catalogues. Then the consumer will compare functions, design and prices of the product and buy it with the lowest price. PriceMeter, a comparative shopping agent, introduced in this paper, is designed best geared to this consumers' buying behavior. Basically, as consumers enter a manufacturer's name, price, features and etc. at a search window, PriceMeter will search the web and provide a list of product informations such as features and prices that meet the search conditions. Consumers can see the information in either a form of catalogue or a printing format. As consumers click specific items to examine closely, it will show prices and information about shopping malls that sell the requested items. Clicking a 'Buy' icon, the consumers will be transferred to the right web page at the linked shopping mall. The emergence of the comparative shopping agent will expedite a consumer-centered retailing economy in the age of e-commerce. As consumers are provided with a better set of product and shopping mall information, they can make better purchasing decisions and gain more bargaining power shifted from manufacturers(sellers). The presentation of this comparative shopping agent is intended to promote the consumer-centered B2C e-commerce.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.29 no.9_10 s.146
• /
• pp.1285-1294
• /
• 2005

This study was fulfilled in the purpose of proposing construction strategies of Internet shopping-mall through the analysis of consumer moving line in Internet shopping-mall. This study was executed in two stages: theoretical study, qualitative study. In the theoretical study, hypothetical Internet shopping behavior model were constructed. Five internet shopping behavior types of apparel : purchase, searching purchase, prepurchase deliberation, information accumulation, opinion leadership and recreation were constructed. Next, consumer decision process were extracted from previous studies and a hypothetical internet shopping behavior model was constructed on the base of consumer decision process and Internet shopping behavior types. And then, through the qualitative study, Internet shopping behavior types were identified and hypothetical model was confirmed after adjustment. For qualitative study, 30 subjects were sampled by focus sampling and investigated by in-depth interview and observation. Seven internet shopping behavior types of apparel were found by the qualitative study: cautious purchase by price comparison, searching purchase, special low price purchase, impulse purchase, prepurchase deliberation, information accumulation and recreation-oriented. On the base of these behavior types, Internet shopping behavior model was adjusted and completed. Finally, according to the results of this study, Internet shopping construction methods that made customer's loyalty high and marketing strategy of Internet shopping-mall were proposed.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.3
• /
• pp.17-23
• /
• 2019

IaaS is well known as a very cost effective computing service which enables required infrastructures to be rented on demand without ownership of real hardwares. It is very suitable for price sensitive services due to pay-per-use style. Operators of such services would want to adjust utilization policy quickly by estimating costs for cloud infrastructures as soon as possible. However, swift response is not possible due to that cloud service providers provide a dozen or so hours delayed billing information. Our work proposes a realtime IaaS cost estimation model based on usages monitored by virtual machine instance. We operate PC laboratory service on a public cloud during full semester to validate our suggested model. From that experiment, an averaged disparity between estimation and actual cost is less than 5.2%.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.239-251
• /
• 2019

Statistical methods such as moving averages, Kalman filtering, exponential smoothing, regression analysis, and ARIMA (autoregressive integrated moving average) have been used for stock market predictions. However, these statistical methods have not produced superior performances. In recent years, machine learning techniques have been widely used in stock market predictions, including artificial neural network, SVM, and genetic algorithm. In particular, a case-based reasoning method, known as k-nearest neighbor is also widely used for stock price prediction. Case based reasoning retrieves several similar cases from previous cases when a new problem occurs, and combines the class labels of similar cases to create a classification for the new problem. However, case based reasoning has some problems. First, case based reasoning has a tendency to search for a fixed number of neighbors in the observation space and always selects the same number of neighbors rather than the best similar neighbors for the target case. So, case based reasoning may have to take into account more cases even when there are fewer cases applicable depending on the subject. Second, case based reasoning may select neighbors that are far away from the target case. Thus, case based reasoning does not guarantee an optimal pseudo-neighborhood for various target cases, and the predictability can be degraded due to a deviation from the desired similar neighbor. This paper examines how the size of learning data affects stock price predictability through k-nearest neighbor and compares the predictability of k-nearest neighbor with the random walk model according to the size of the learning data and the number of neighbors. In this study, Samsung electronics stock prices were predicted by dividing the learning dataset into two types. For the prediction of next day's closing price, we used four variables: opening value, daily high, daily low, and daily close. In the first experiment, data from January 1, 2000 to December 31, 2017 were used for the learning process. In the second experiment, data from January 1, 2015 to December 31, 2017 were used for the learning process. The test data is from January 1, 2018 to August 31, 2018 for both experiments. We compared the performance of k-NN with the random walk model using the two learning dataset. The mean absolute percentage error (MAPE) was 1.3497 for the random walk model and 1.3570 for the k-NN for the first experiment when the learning data was small. However, the mean absolute percentage error (MAPE) for the random walk model was 1.3497 and the k-NN was 1.2928 for the second experiment when the learning data was large. These results show that the prediction power when more learning data are used is higher than when less learning data are used. Also, this paper shows that k-NN generally produces a better predictive power than random walk model for larger learning datasets and does not when the learning dataset is relatively small. Future studies need to consider macroeconomic variables related to stock price forecasting including opening price, low price, high price, and closing price. Also, to produce better results, it is recommended that the k-nearest neighbor needs to find nearest neighbors using the second step filtering method considering fundamental economic variables as well as a sufficient amount of learning data.