• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.6
• /
• pp.253-260
• /
• 2015

When we buy items in online stores, it is common to face recommended items that meet our interest. These recommendation system help users not only to find out related items, but also find new things that may interest users. Recommendation system has been widely studied and various models has been suggested such as, collaborative filtering and content-based filtering. Though collaborative filtering shows good performance for predicting users preference, there are some conditions where collaborative filtering cannot be applied. Sparsity in user data causes problems in comparing users. Systems which are newly starting or companies having small number of users are also hard to apply collaborative filtering. Content-based filtering should be used to support this conditions, but content-based filtering has some drawbacks and weakness which are tendency of recommending similar items, and keeping history of a user makes recommendation simple and not able to follow up users preference changes. To overcome this drawbacks and limitations, we suggest weighted window assisted user history based recommendation system, which captures user's purchase patterns and applies them to window weight adjustment. The system is capable of following current preference of a user, removing useless recommendation and suggesting items which cannot be simply found by users. To examine the performance under user and data sparsity environment, we applied data from start-up trading company. Through the experiments, we evaluate the operation of the proposed recommendation system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.12
• /
• pp.2871-2877
• /
• 2015

Shopping patterns are changing with the emergence of SNS. Recently, it is also interested in providing the information based on the users' needs. Generally, the provided information is obtained from the history of users' simple browsing. Best selling hot item list is also provided in order to reflect the preferences of public users. However, the provided information is irrelevant to an individual preference. In this paper, we propose a method to utilize inner and outer SNS for analyzing public preferences about goods which are interested by individual users. The inner analyzing module collects and analyzes the preferences of community members about two goods designated by individual users. The outer analyzing module supports to analyze public preferences by using the tweeter SNS. The results of implementation show that it is possible to recommend goods based on the individual users' preferences unlike the existing shopping mall.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.7C
• /
• pp.619-626
• /
• 2012

With the service suggesting additional extended or related query, search engines aim to provide their users more convenience. The extended or related query suggestion service based on popularity, or by how many people have searched on web using the query, has limitations to elevate users' satisfaction, because each user's preference and interests differ. This paper will demonstrate the design and realization of the system that suggests extended query appropriate for users' demands, and also an improvement in the computing process between entering the first search word and the subsequent extension to the related themes. According to the evaluation the proposed system suggested 41% more extended or related query than when searching on Google, and 48% more than on Yahoo. Also by improving the shortcomings of the extended or related query system based on general popularity rather than each user's preference, the new system enhanced users' convenience further.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.8
• /
• pp.45-50
• /
• 2018

Many of the current successful commercial recommender systems utilize collaborative filtering techniques. This technique recommends products to the active user based on product preference history of the neighbor users. Those users with similar preferences to the active user are typically named his/her neighbors. Hence, finding neighbors is critical to performance of the system. Although much effort for developing similarity measures has been devoted in the literature, there leaves a lot to be improved, especially in the aspect of handling subjectivity or vagueness in user preference ratings. This paper addresses this problem and presents a novel similarity measure using fuzzy logic for selecting neighbors. Experimental studies are conducted to reveal that the proposed measure achieved significant performance improvement.

• 한국경영정보학회:학술대회논문집
• /
• 2008.06a
• /
• pp.35-51
• /
• 2008

This study is to investigate factors that affect preference to CMDS(convergence mobile data service) on institutionalization of MDS. A research model was proposed and subsequent hypotheses were empirically tested with partial least square (PLS) based on 400 responses from the users of CMDS(DMB: 200 / m-Banking: 200). It was learned that institutionalization of technology related building MDS was positively associated with assimilation of MDS(represent a institutionalization of MDS) rather than service quality and use gratification. It means that users decided use of MDS refereed from its level of assimilation to MDS channel. Also, attractiveness of alternatives to CMDS is negatively associated with continuous use of CMDS and preference to CMDS. Lastly, their association strength was partially moderated by the type of motivation for using CMDS.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.7
• /
• pp.2161-2168
• /
• 2000

Since most of the existing web cache structures are static, they cannot support the dynamic request change of he current WWW users well. Users re generally using multiple programs in several different windows with rapid preference change within a relatively short period of time. We develop a network-path based algorithm. It organizes a cache according to the network path of the requested URLs and build a network cache farm where caches are logically connected with each other and each cache has its own preference over certain network paths. The algorithm has been implemented and tested in a real site. The performance results show that the new algorithm outperforms the existing static algorithms in the hit ratio and response time dramatically.

• Proceedings of the Safety Management and Science Conference
• /
• 2011.11a
• /
• pp.695-716
• /
• 2011

In the future, smartphone convergences are not only based on the on/offline integration, but also with the integration between mobile communications and broadcasts. Therefore, there is a need to search for new direction of mobile device that enables variety user applications that are different from the existing size and application issue. The aim of this reserch is to improve user interface of smartphone's functional attribute. The survey results in this paper showed that the most preferable attribute of smartphone among the 8 was the wireless internet 25.3%, followed by messaging 20% and application 19.8%, which totaled to 62.5%. But the samples used were mostly limited to those aged 20 through 30. So the results are not considered as a representative preference of all smartphone users, and should be considered otherwise before materializing them to a product. Therefore, for the more liable results the further research should be conducted to gather data from a variety of users of all ages, and the functional attribute should be analysed through QFD.

• Journal of the Korean Home Economics Association
• /
• v.43 no.10 s.212
• /
• pp.155-165
• /
• 2005

The purpose of this study was to analyze difference in clothing preference based on the perceived body types. The objects of this study were to prepare for the establishment of a marketing strategy and alternative plan intended for users operating in a subdivided market, after analyzing the differences in clothing preference based on the perceived body types. The respondents comprised 192 female adults, who were residents in Busan. The questionnaire was composed of three sections: style, textile, and color of clothing. Data were analyzed by frequency, factor analysis, cluster analysis, discriminate analysis, and ANOVA. Cluster analysis was employed to identify groups of respondents based on the five delineated measure items. Based on the findings, three distinct groups were formed: thin, normal, and obese. The result of this study showed statistically significant differences among the three groups in terms of style, textile, and color of clothing, as well as in terms of demographic characteristics. Marketing and management implications for effectively targeting the segments are discussed.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.04a
• /
• pp.104-108
• /
• 2000

The paper sets the goal as understanding relationship between usability and subjective preference with the cross- cultural comparison between korea and Japan. Total 42 Korean and japanese housewives participated in the experiment where subjects evaluated their subjective preferences on 16 different variations of computer-simulated microwave ovens. In additions, subjects also performed usability testing over 9 different microwave ovens with 6 different tasks given to users. Subjective preferences and usability were analyzed by Conjoint analysis to identify relative importance of features. The results showed that, in case of Korean subjects, subjective preference has positive relationship with usability (i.e. aesthetically good product also showed better performance in usability testing).However, Japanese subjects showed the tendency that subjectively preferred products are not necessarily evaluated good in usability testing (i.e. god aesthetic is one thing and high usability is another). this difference leads the speculation that culture plays a role in balancing the relationship between aesthetic and functionality.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.641-642
• /
• 2008

In this paper, we propose a new approach for the implicit rating algorithm of finding user's intense and preference to the contents on the web. Although the explicit method dig out the user preference of specific contents based on the user's intervention, we propose the implicit method obtaining the user preference according to the user's behavioral patterns on the web implicitly and automatically without the user's intervention. The implementation results show that the proposed approach is highly valuable for supporting recommender systems in conjunction with the users lifestyle.