• 제목/요약/키워드: user preferences

Search Result 508, Processing Time 0.02 seconds

The preference of Interior space of the consumers's characteristics among Apartment (소비자 특성에 따른 아파트 실내 공간 선호)

  • 김미희;이유미
    • Korean Institute of Interior Design Journal
    • /
    • no.21
    • /
    • pp.101-106
    • /
    • 1999
  • This study has been designed to explore the preferences of interior space for those living in apartment housing. It also examines the relationships between preferences of interior space, such as storage space, organization type of LDK(the living room, the dining room, and kitchen), space facing south, an interior garden, the concept of each room and the characteristics of the consumers, such as age, educational background employment status of homemakers, occupation of the primary income provider, family-life cycle, total household income, the size of floor space, and homeownership. In conclusion, this study suggests that at the time of designing apartment housing units, serious consideration should be given to the built-in closets or storage space in the anbang and to the location of a child's room facing to the south of the dwelling, especially for the families with a child attending primary school or younger and higher education level of homemaker. This study also recommends that the organization of the living room, the dining room, and the kitchen should be varied according to the housing size and the age of homemaker.

  • PDF

A Matchmaking System Adjusting the Mate-Selection Criteria based on a User's Behaviors using the Decision Tree (고객의 암묵적 이상형을 반영하여 배우자 선택기준을 동적으로 조정하는 온라인 매칭 시스템: 의사결정나무의 활용을 중심으로)

  • Park, Yoon-Joo
    • Information Systems Review
    • /
    • v.14 no.3
    • /
    • pp.115-129
    • /
    • 2012
  • A matchmaking system is a type of recommender systems that provides a set of dating partners suitable for the user by online. Many matchmaking systems, which are widely used these days, require users to specify their preferences with regards to ideal dating partners based on criteria such as age, job and salary. However, some users are not aware of their exact preferences, or are reluctant to reveal this information even if they do know. Also, users' selection standards are not fixed and can change according to circumstances. This paper suggests a new matchmaking system called Decision Tree based Matchmaking System (DTMS) that automatically adjusts the stated standards of a user by analyzing the characteristics of the people the user chose to contact. AMMS provides recommendations for new users on the basis of their explicit preferences. However, as a user's behavioral records are accumulated, it begins to analyze their hidden implicit preferences using a decision tree technique. Subsequently, DTMS reflects these implicit preferences in proportion to their predictive accuracy. The DTMS is regularly updated when a user's data size increases by a set amount. This paper suggests an architecture for the DTMS and presents the results of the implementation of a prototype.

  • PDF

Cody Recommendation System Using Deep Learning and User Preferences

  • Kwak, Naejoung;Kim, Doyun;kim, Minho;kim, Jongseo;Myung, Sangha;Yoon, Youngbin;Choi, Jihye
    • International Journal of Advanced Culture Technology
    • /
    • v.7 no.4
    • /
    • pp.321-326
    • /
    • 2019
  • As AI technology is recently introduced into various fields, it is being applied to the fashion field. This paper proposes a system for recommending cody clothes suitable for a user's selected clothes. The proposed system consists of user app, cody recommendation module, and server interworking of each module and managing database data. Cody recommendation system classifies clothing images into 80 categories composed of feature combinations, selects multiple representative reference images for each category, and selects 3 full body cordy images for each representative reference image. Cody images of the representative reference image were determined by analyzing the user's preference using Google survey app. The proposed algorithm classifies categories the clothing image selected by the user into a category, recognizes the most similar image among the classification category reference images, and transmits the linked cody images to the user's app. The proposed system uses the ResNet-50 model to categorize the input image and measures similarity using ORB and HOG features to select a reference image in the category. We test the proposed algorithm in the Android app, and the result shows that the recommended system runs well.

A Formal Study on Game Character Preference through Game User Classification (게임 이용자의 특성 분류를 통한 게임 캐릭터 선호도에 관한 조형 연구)

  • Noh, Kyung-Hee;Lee, Tae-Il;Cho, Sung-Hyun
    • Journal of Korea Game Society
    • /
    • v.7 no.4
    • /
    • pp.23-31
    • /
    • 2007
  • The study is to explore the ways to design game characters according to the tendency of game users by classifying game users and analyzing the relation between user classes and their preferences towards game characters. The study examines various user classifications based on users' engagement levels, and designs a user questionnaire from them. Based on the result of questionnaire analysis, the study redefines user classes and applies the formal elements of character design to draw on the relationships between user classes and their preferences.

  • PDF

(Efficient Methods for Combining User and Article Models for Collaborative Recommendation) (협력적 추천을 위한 사용자와 항목 모델의 효율적인 통합 방법)

  • 도영아;김종수;류정우;김명원
    • Journal of KIISE:Software and Applications
    • /
    • v.30 no.5_6
    • /
    • pp.540-549
    • /
    • 2003
  • In collaborative recommendation two models are generally used: the user model and the article model. A user model learns correlation between users preferences and recommends an article based on other users preferences for the article. Similarly, an article model learns correlation between preferences for articles and recommends an article based on the target user's preference for other articles. In this paper, we investigates various combination methods of the user model and the article model for better recommendation performance. They include simple sequential and parallel methods, perceptron, multi-layer perceptron, fuzzy rules, and BKS. We adopt the multi-layer perceptron for training each of the user and article models. The multi-layer perceptron has several advantages over other methods such as the nearest neighbor method and the association rule method. It can learn weights between correlated items and it can handle easily both of symbolic and numeric data. The combined models outperform any of the basic models and our experiments show that the multi-layer perceptron is the most efficient combination method among them.

A Playlist Generation System based on Musical Preferences (사용자의 취향을 고려한 음악 재생 목록 생성 시스템)

  • Bang, Sun-Woo;Kim, Tae-Yeon;Jung, Hye-Wuk;Lee, Jee-Hyong;Kim, Yong-Se
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.20 no.3
    • /
    • pp.337-342
    • /
    • 2010
  • The rise of music resources has led to a parallel rise in the need to manage thousands of songs on user devices. So users are tend to build play-list for manage songs. However the manual selection of songs for creating play-list is bothersome task. This paper proposes an auto play-list recommendation system considering user's context of use and preference. This system has two separate systems: mood and emotion classification system and music recommendation system. Users need to choose just one seed song for reflection their context of use and preference. The system recommends songs before the current song ends in order to fill up user play-list. User also can remove unsatisfied songs from recommended song list to adapt user preferences of the system for the next recommendation precess. The generated play-lists show well defined mood and emotion of music and provide songs that user preferences are reflected.

Friend Recommendation Scheme Using Moving Patterns of Mobile Users in Social Networks (소셜 네트워크에서 모바일 사용자 이동 패턴을 이용한 친구 추천 기법)

  • Bok, Kyoungsoo;Seo, Kiwon;Lim, Jongtae;Yoo, Jaesoo
    • The Journal of the Korea Contents Association
    • /
    • v.16 no.4
    • /
    • pp.56-64
    • /
    • 2016
  • With the development of information technologies and the wide spread of smart devices, the number of users of social network services has increased exponentially. Studies that identify user preferences and recommend similar users in these social network services have been actively done. In this paper, we propose a new scheme to recommend social network friends with similar preferences through the moving pattern analysis of mobile users. The proposed scheme removes the meaningless trajectories via companions, short time trajectories, and repeated trajectories to determine the correct user preference. The proposed scheme calculates user similarity using the meaningful trajectories and recommends users with similar preferences as friends. It is shown through performance evaluation that the proposed scheme outperforms the existing schemes.

An Event Recommendation Scheme Using User Preference and Collaborative Filtering in Social Networks (소셜 네트워크에서 사용자 성향 및 협업 필터링을 이용한 이벤트 추천 기법)

  • Bok, Kyoungsoo;Lee, Suji;Noh, Yeonwoo;Kim, Minsoo;Kim, Yeonwoo;Lim, Jongtae;Yoo, Jaesoo
    • KIISE Transactions on Computing Practices
    • /
    • v.22 no.10
    • /
    • pp.504-512
    • /
    • 2016
  • In this paper, we propose a personalized event recommendation scheme using user's activity analysis and collaborative filtering in social network environments. The proposed scheme predicts un-evaluated attribute values through analysis of user activities, relationships, and collaborative filtering. The proposed scheme also incorporates a user's recent preferences by considering the recent history for the user or context-aware information to precisely grasp the user's preferences. As a result, the proposed scheme can recommend events to users with a high possibility to participate in new events, preventing indiscriminate recommendations. In order to show the superiority of the proposed scheme, we compare it with the existing scheme through performance evaluation.

Analysis of Virtual Fashion Style Preferences and Purchasing Behavior of Metaverse Platform 'Zepeto' Users (메타버스 플랫폼 '제페토' 이용자의 가상패션 스타일 선호도 및 구매행태 분석)

  • Kim, Kaya;Seong, Okjin;Kim, Sookjin
    • Journal of Fashion Business
    • /
    • v.26 no.3
    • /
    • pp.33-49
    • /
    • 2022
  • In the metaverse, it is important to embellish aesthetics of user with a character called 'Avatar', a virtual representation of the user. This study provides basic data related to the fashion trend of the metaverse by studying 'Zepeto', a representative Korean platform. For empirical research, Zepeto's "Best Items" section were investigated and analyzed in the first pre-survey. Based on this, the second and main survey was conducted using a questionnaire to investigate users' style-specific preferences and purchasing behaviors for virtual fashion, comparing style preferences between virtual and real, brand preferences, and purchasing behaviors of virtual fashion. The survey found that most users were teenage girls with a high preference for pastel-toned, feminine, and cute casual styles who had a much higher interest in brands bearing idol names than in real-world luxury brands. Many responded that they felt burdened by purchasing items that had to be purchased for cash. The same can be assumed to be the reason why they preferred a suit of items that were fully coordinated rather than individual items. These results seem to reflect characteristics of teenage girls who lack cash with a high preference for idols and feminine-cute casual styles. This study suggests considerations when creating virtual fashion items. By providing basic information, more effects and developments in creating virtual fashion items that reflect consumer preferences and reactions are expected in the future.