• Journal of Korea Multimedia Society
• /
• v.25 no.2
• /
• pp.257-268
• /
• 2022

When there is a missing value in the raw data, if ignore the missing values and proceed with the analysis, the accuracy decrease due to the decrease in the number of sample. The method of imputation and analyzing patterns and significant values can compensate for the problem of lower analysis quality and analysis accuracy as a result of bias rather than simply removing missing values. In this study, we proposed to study irregular data patterns and missing processing methods of data using machine learning techniques for the study of correction of missing values. we would like to propose a plan to replace the missing with data from a similar past point in time by finding the situation at the time when the missing data occurred. Unlike previous studies, data correction techniques present new algorithms using DNN and KNN-MLE techniques. As a result of the performance evaluation, the ANAE measurement value compared to the existing missing section correction algorithm confirmed a performance improvement of about 0.041 to 0.321.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.18 no.3
• /
• pp.99-111
• /
• 2016

In order to use cosmetics brands SNS effectively and establish strategy, the purpose of this study is to provide consumer date. According to cosmetics consumption value groups, this study examined each cosmetics consumption value group's level of concern of three cosmetics brands SNS features, informativity, enjoyment and interactivity. For the data, questionnaire was collected by 198 women, and the data were measured by ANOVA, factor analysis, cluster analysis and Ducan test. According to cluster analysis cosmetics consumption value groups were divided into four groups, unconcern group, hedonic value pursuit group, function of brand value pursuit group, high concern group. The results of the study are as follows: First, high concern group thought highly of all cosmetics brands SNS features, including informativity, enjoyment and interactivity. In addition all consumer groups were concerned informativity rather then enjoyment and interactivity. Second, comparing with high concern group, other groups which include unconcern group, hedonic value pursuit group and function of brand value pursuit group were not concerned about cosmetics brands SNS features' enjoyment and interactivity. Except informativity, hedonic value pursuit group and unconcern group were more concerned interactivity than enjoyment. While, high concern group and function of brand value pursuit group were more concerned enjoyment than interactivity.

• Fashion & Textile Research Journal
• /
• v.10 no.3
• /
• pp.316-321
• /
• 2008

The purpose of this study is to find what male consumers value in their clothing behaviors, as well as to investigate how the consumers' shopping values and store VM impact on their clothing purchase behaviors. For data collection, research questionnaires were responded by 202 male students living in Busan. The collected data were analyzed according to the frequency-factor analysis using SPSS for win 10.1 Package, the factor analysis using Varimax, reliability analysis, and multi-regression analysis. The results of this study are as follows; First, the shopping values were composed of hedonic, utilitarian, and economic value, and VM was divided into store facility, store image, layout, and fashion information. Second, multi-regression analysis was conducted to find the impact of consumers' shopping values on their clothing purchase behaviors. The result showed that the hedonic shopping value and utilitarian shopping value significantly affected the consumers' clothing purchase behaviors, while economics shopping value did not show any statistical significance. Third, multi-regression analysis was conducted to find the impact of store VM on consumers' clothing purchase behaviors. The result showed that store image, layout, and fashion information had a significant impact on consumers' clothing purchase behaviors.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.4
• /
• pp.1099-1106
• /
• 2006

This study is an analysis of the stock trading value in terms of investor types in the Korean stock market for recent 12 years. We examined the characteristics in stock trading value variation according to each investor type and the interactive relationship in the trading value between types of investors. The results show that the trading value scale of every investor type increases overall while the proportion of the trading value by each investor type in the market exhibits variation. In addition, a statistically significant interactive relationship in the trading value between types of investors exists: the correlations are formed differently before and after events which largely influence the stock market.

• Journal of Information Technology Services
• /
• v.18 no.1
• /
• pp.113-130
• /
• 2019

Data can be considered a core driver of the Fourth Industrial Revolution, and databases are needed to create value by efficiently obtaining, storing and analyzing the data. However, there are currently no adequate valuation methods to handle databases. This study aims first, to understand databases as the subject of valuation and analyze value drivers of databases, and second, to propose a database valuation model based on this finding. To this end, we derive value drivers of databases from the characteristics and value criteria of databases observed in previous studies. Based on survey data from 396 database service firms we verify the value drivers through linear regression analysis. We find that the annual growth rate in database capacity and the data types positively affect sales of databases and offer ways to utilize them when estimating the cash flow, which is the variable to apply the discounted cash flow method-based income approach. This study contributes empirical insights into how to valuate databases considering their value drivers.

• Fashion & Textile Research Journal
• /
• v.12 no.4
• /
• pp.431-438
• /
• 2010

This study analyzes how the environmental values of fashion consumers influence the purchase satisfaction and repurchase intention of eco-friendly fashion products. The survey was conducted from June $1^{st}$ to $30^{th}$ in 2009, and 343 responses were used in the data analysis. The statistical analysis methods were frequency analysis, factor analysis, reliability analysis, and multiple regression analysis. The results show that the environmental values is classified by environment conservative value, economical value, social altruistic value, and egocentric value. The social altruistic value of fashion consumers affects purchase satisfaction of eco-friendly fashion products. The social altruistic value, environment conservative value, and egocentric value affect the repurchase intention of eco-friendly fashion products.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.33 no.5
• /
• pp.782-792
• /
• 2009

The purpose of this research were 1) to identify the distribution of customer equity about sports fashion brands, 2) to identify the dimensions of fashion brand attributes influencing customer satisfaction and customer equity, and 3) to investigate relationships among sports fashion attributes, customer satisfaction and customer equity. Survey questionnaire was used to collect data and 900 responses were used for the data analysis. Descriptive statistics(i.e., frequency, percentage), factor analysis and multiple regression analysis were used for the data analysis. The results of this study were as following. First, 67.4%(i.e., outdoor sports brands) of customer equity distributes under 1 million won while 61.3%(i.e., general sports brand) and 54.3%(i.e., golf brands) distributes. Second, the sportswear brand dimensions consist of 6 factors, product quality value, convenience value, perceived value, unique brand image, trust relationship, and personalized relationship. Third, the higher the product quality value, perceived value, unique brand image, and trust relationship were, the higher customer satisfaction was. Fourth, the higher customer satisfaction was, the higher customer equity was.

• Korean Journal of Human Ecology
• /
• v.17 no.4
• /
• pp.759-769
• /
• 2008

The purpose of this study was to classify consumption value and analyze the relationship between consumption value typology and fashion product purchasing behavior of college students as consumers. Data were gathered by surveying college students living in Daegu and Kyungbook area using convenient sampling, and 513 questionnaires were used in the statistical analysis. Data were analyzed by frequency, factor analysis, cluster analysis, ANOVA, Duncan-test, Chi-square, and t-test. The findings are as follows. According to the consumption value typologies of college students were classified into three groups such as Social Value oriented, Functional Value oriented, and Differentiated Individuality oriented group. The Social Value oriented group and the Differentiated Individuality oriented group were more conscious of clothing pursuit propensities behavior such as brand, shopping place, and price than Functional Value oriented group. The Functional Value oriented group showed the lowest interest in brand name. Purchasing behavior of casual wear and bags fashion product had the significant effects on the shopping place, and price.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.218-223
• /
• 2021

The five elements of big data are said to be Volume, Variety, Velocity, Veracity, and Value. Among them, data lacking the Veracity of the data or fake data not only makes an error in decision making, but also hinders the creation of value. This study analyzed YouTube's revenue structure to focus the effect of data integrity on data valuation among these five factors. YouTube is one of the OTT service platforms, and due to COVID-19 in 2020, YouTube creators have emerged as a new profession. Among the revenue-generating models provided by YouTube, the process of generating advertising revenue based on click-based playback was analyzed. And, analyzed the process of subtracting the profits generated from invalid activities that not the clicks due to viewers' pure interests, then paying the final revenue. The invalid activity in YouTube's revenue structure is Raw Data, not pure viewing activity of viewers, and it was confirmed a direct impact on revenue generation. Through the analysis of this process, the new Data Value Chain was proposed.

• The Journal of Information Systems
• /
• v.32 no.1
• /
• pp.1-21
• /
• 2023

Purpose The purpose of this study is to investigate the intention of early application users in consideration of the characteristics of digital finance-based MyData service users. It is expected that user characteristics will affect the intention to use MyData service, which has not yet been advanced, and accordingly, it will examine how the characteristics of the initial users of MyData service and the intention to use it are connected. Design/methodology/approach The model used in this study is a value-based adoption model (VAM), and a lot of research has been conducted on information technology and online user acceptance and continuous use intention of online users. VAM has been proven useful through empirical analysis in many studies. The value-based acceptance model is a method of analyzing the intention to use Benefits and Sacrifices as the main elements of perceived value. It can be said to be a model that can analyze the benefits of use and the sacrifices to be made. Findings According to the analysis results of this study, it was found that usefulness, enjoyment, and reliability, which are the benefits of MyData service apps, had a positive effect on perceived value, which is partially consistent with existing research results. However, it was found that complexity, which is the sacrifice of MyData service apps, negatively affects perceived value and security has no negative impact. The results of security are considered to be complementary to financial institutions because MyData service deals with financial data based on personal information, and the research hypothesis is rejected because users' demands are relatively low. Therefore, MyData service apps should do more to increase benefits (usefulness, enjoyment, and reliability) than to reduce sacrifice (complexity) to users.