• Journal of Intelligence and Information Systems
• /
• v.15 no.1
• /
• pp.123-140
• /
• 2009

Collaborative filtering recommends products using customers' preferences, so it cannot recommend products to the new customer who has no preference information. This paper proposes a novel approach to new customer recommendations using the social network analysis which is used to search relationships among social entities such as genetics network, traffic network, organization network, etc. The proposed recommendation method identifies customers most likely to be neighbors to the new customer using the centrality theory in social network analysis and recommends products those customers have liked in the past. The procedure of our method is divided into four phases : purchase similarity analysis, social network construction, centrality-based neighborhood formation, and recommendation generation. To evaluate the effectiveness of our approach, we have conducted several experiments using a data set from a department store in Korea. Our method was compared with the best-seller-based method that uses the best-seller list to generate recommendations for the new customer. The experimental results show that our approach significantly outperforms the best-seller-based method as measured by F1-measure.

• Journal of Broadcast Engineering
• /
• v.17 no.2
• /
• pp.270-283
• /
• 2012

With the advent of multi-channel TV, IPTV and smart TV services, excessive amounts of TV program contents become available at users' sides, which makes it very difficult for TV viewers to easily find and consume their preferred TV programs. Therefore, the service of automatic TV recommendation is an important issue for TV users for future intelligent TV services, which allows to improve access to their preferred TV contents. In this paper, we present a recommendation model based on statistical machine learning using a collaborative filtering concept by taking in account both public and personal preferences on TV program contents. For this, users' preference on TV programs is modeled as a latent topic variable using LDA (Latent Dirichlet Allocation) which is recently applied in various application domains. To apply LDA for TV recommendation appropriately, TV viewers's interested topics is regarded as latent topics in LDA, and asymmetric Dirichlet distribution is applied on the LDA which can reveal the diversity of the TV viewers' interests on topics based on the analysis of the real TV usage history data. The experimental results show that the proposed LDA based TV recommendation method yields average 66.5% with top 5 ranked TV programs in weekly recommendation, average 77.9% precision in bimonthly recommendation with top 5 ranked TV programs for the TV usage history data of similar taste user groups.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.6
• /
• pp.163-172
• /
• 2012

Collaborative filtering which is used explicit method in a existing recommedation system, can not only reflect exact attributes of item but also still has the problem of sparsity and scalability, though it has been practically used to improve these defects. This paper proposes the personalized recommendation system using RFM method and k-means clustering in u-commerce which is required by real time accessablity and agility. In this paper, using a implicit method which is is not used complicated query processing of the request and the response for rating, it is necessary for us to keep the analysis of RFM method and k-means clustering to be able to reflect attributes of the item in order to find the items with high purchasablity. The proposed makes the task of clustering to apply the variable of featured vector for the customer's information and calculating of the preference by each item category based on purchase history data, is able to recommend the items with efficiency. To estimate the performance, the proposed system is compared with existing system. As a result, it can be improved and evaluated according to the criteria of logicality through the experiment with dataset, collected in a cosmetic internet shopping mall.

• 대한공업교육학회지
• /
• v.39 no.2
• /
• pp.37-57
• /
• 2014

This study investigated perception of first-year college students who recently experienced technology education in their secondary education for describing contemporary technology classrooms. To accomplish this goal, survey and in-depth interview on their technology classrooms were employed. Participants in this study were 427 first-year college students who began their college life in 2013 and consisted of 224 students enrolled in 10 departments of educational major and 203 students who enrolled in 9 departments of other colleges. The instrument of this study consisted of preference toward technology classrooms and teachers, experience in the secondary technology classrooms, perception toward technology teachers, and suggestions for technology classrooms with five point Likert scales and open-ended questionnaires. And individual in-depth interviews with 22 volunteers who answered the instrument and consented the interview process were conducted. Based on the collected data, statistical and theme analyses were performed and the key findings were as follows. First-year students' experiences for technology classrooms were described with the theme of 'learning contents or activities'(54.4%). And the negative perception toward technology classrooms(29.1%) was larger than he positive perception(16.5%). The perception toward technology classrooms was also presented with two themes of teaching methods and subject interest. The perception toward technology teachers presented a medium level preference with several themes of teachers' teaching methods, teachers' personality, and subject interest. Lecture style method(60.48%) was largely used in the participants' technology classrooms and problem solving or collaborative methods was not frequent(19.31%). The participants indicated a need for improving teaching methods in technology education and suggested sufficient administration and curriculum supports and transitions of the learning contents. Further studies investigating the diverse public's perception toward technology and technology classrooms could be recommended.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.111-128
• /
• 2023

With the development of artificial intelligence technology, interest in data-based product preference estimation and personalized recommender systems is increasing. However, if the recommendation is not suitable, there is a risk that it may reduce the purchase intention of the customer and even extend to a huge financial loss due to the characteristics of the financial product. Therefore, developing a recommender system that comprehensively reflects customer characteristics and product preferences is very important for business performance creation and response to compliance issues. In the case of financial products, product preference is clearly divided according to individual investment propensity and risk aversion, so it is necessary to provide customized recommendation service by utilizing accumulated customer data. In addition to using these customer behavioral characteristics and transaction history data, we intend to solve the cold-start problem of the recommender system, including customer demographic information, asset information, and stock holding information. Therefore, this study found that the model proposed deep learning-based collaborative filtering by deriving customer latent preferences through characteristic information such as customer investment propensity, transaction history, and financial product information based on customer transaction log records was the best. Based on the customer's financial investment mechanism, this study is meaningful in developing a service that recommends a high-priority group by establishing a recommendation model that derives expected preferences for untraded financial products through financial product transaction data.

• Journal of Digital Contents Society
• /
• v.15 no.2
• /
• pp.227-235
• /
• 2014

The change from people's work-centered values to their leisure-centered values leads into the change in their life styles. In the circumstance, people's participation into sports activities seems to be an important means to improve their quality of life. Along with the change of the times, more people take part in water leisure sports including kayak. As a result, people's needs for various designs of water leisure goods are on the rise. In this sense, it is necessary to come up with strategies to actively respond to such a change. In this paper, we proposed a user decision-making support system for designing kayaks for leisure. Based on the previous studies and literatures and a questionnaire survey with consumers, it chose the sensitivity related to design. By conducting factor analysis and evaluation, it drew sensitivity and proposed kayak design layouts in the aspect of customer sensitivity preference. It is expected that the result of this study will be used not only for kayak design, but as a design guide for the equipment of water leisure sports, and will be applied for user-friendly design.

• Journal of Digital Contents Society
• /
• v.14 no.4
• /
• pp.419-428
• /
• 2013

Real-time accessibility and agility are required in u-commerce under ubiquitous computing environment. Most of the existing recommendation techniques adopt the method of evaluation based on personal profile, which has been identified with difficulties in accurately analyzing the customers' level of interest and tendencies, as well as the problems of cost, consequently leaving customers unsatisfied. Researches have been conducted to improve the accuracy of information such as the level of interest and tendencies of the customers. However, the problem lies not in the preconstructed database, but in generating new and diverse profiles that are used for the evaluation of the existing data. Also it is difficult to use the unique recommendation method with hierarchy of each customer who has various characteristics in the existing recommendation techniques. Accordingly, this dissertation used the implicit method without onerous question and answer to the users based on the data from purchasing, unlike the other evaluation techniques. We applied FRAT technique which can analyze the tendency of the various personalization and the exact customer.

• Korean Business Review
• /
• v.20 no.1
• /
• pp.145-168
• /
• 2007

Recommender system helps customers to find easily items and helps the e-biz companies to set easily their target customer by automated recommending process. Recommender systems are being adopted by several e-biz companies and from these systems, both of customers and companies take some benefits. This study sets several thresholds to the similarity weight, which indicates a degree of similarity of two customers' preference, to improve the performance of prediction accuracy. According to the threshold, the accuracy of prediction is being improved but some threshold setting shows the reduction of the prediction rate, which is the coverage. This coverage reduction has male effect on the prediction accuracy of customers, so more study on the prediction accuracy of recommender system and to maximize the coverage are needed.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.1
• /
• pp.38-46
• /
• 2009

With the rapid increase in the number of Web documents, the problem of information overload is growing more serious in Internet search. In order to ease the problem, researchers are paying attention to personalization, which creates Web environment fittingly for users' preference, but most of search engines produce results focused on users' queries. Thus, the present study examined the method of producing search results personalized based on a user's understanding level. A characteristic that differentiates this study from previous researches is that it considers users' understanding level and searches documents of difficulty fit for the level first. The difficulty level of a document is adjusted based on the understanding level of users who access the document, and a user's understanding level is updated periodically based on the difficulty of documents accessed by the user. A Web search system based on the results of this study is expected to bring very useful results to Web users of various age groups.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.1
• /
• pp.104-109
• /
• 2005

Context-awareness is an important element that can provide service of good quality according to users' surrounding environment and status in ubiquitous computing environment. Information gathering tools for context-awareness use small size mobile devices which have easy movement and a mobile agent in mobile device. Now, Mobile agents are consuming much times and expense to collect and recognize each users' context information. Therefore, needs research about structure for users' context information awareness in early time to reduce mobile agent's load. This paper proposes a P2P mobile agent structure that mikes filtering techniques and a P2P agent in mobile agent. The proposed structure analyzes each user's context information in same area, and groups users who have similar preference degree. Grouped users share information using a P2P mobile agent. Also this structure observes and learns to continue on users' action and service, and measures new interrelation.