• Title/Summary/Keyword: explicit preference

Search Result 4, Processing Time 0.067 seconds

Proactive: Comprehensive Access to Job Information

  • Lee, Danielle;Brusilovsky, Peter
    • Journal of Information Processing Systems
    • /
    • v.8 no.4
    • /
    • pp.721-738
    • /
    • 2012
  • The Internet has become an increasingly important source for finding the right employees, so more and more companies post their job openings on the Web. The large amount and dynamic nature of career recruiting information causes information overload problems for job seekers. To assist Internet users in searching for the right job, a range of research and commercial systems were developed over the past 10 years. Surprisingly, the majority of existing job search systems support just one, rarely two ways of information access. In contrast, our work focused on exploring a value of comprehensive access to job information in a single system (i.e., a system which supports multiple ways). We designed Proactive, a recommendation system providing comprehensive and personalized information access. To assist the varied needs of users, Proactive has four information retrieval methods - a navigable list of jobs, keyword-based search, implicit preference-based recommendations, and explicit preference-based recommendations. This paper introduces the Proactive and reports the results of a study focusing on the experimental evaluation of these methods. The goal of the study was to assess whether all of the methods are necessary for users to find relevant jobs and to what extent different methods can meet different users' information requirements.

Method to Improve Data Sparsity Problem of Collaborative Filtering Using Latent Attribute Preference (잠재적 속성 선호도를 이용한 협업 필터링의 데이터 희소성 문제 개선 방법)

  • Kwon, Hyeong-Joon;Hong, Kwang-Seok
    • Journal of Internet Computing and Services
    • /
    • v.14 no.5
    • /
    • pp.59-67
    • /
    • 2013
  • In this paper, we propose the LAR_CF, latent attribute rating-based collaborative filtering, that is robust to data sparsity problem which is one of traditional problems caused of decreasing rating prediction accuracy. As compared with that existing collaborative filtering method uses a preference rating rated by users as feature vector to calculate similarity between objects, the proposed method improves data sparsity problem using unique attributes of two target objects with existing explicit preference. We consider MovieLens 100k dataset and its item attributes to evaluate the LAR_CF. As a result of artificial data sparsity and full-rating experiments, we confirmed that rating prediction accuracy can be improved rating prediction accuracy in data sparsity condition by the LAR_CF.

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

Using Mixed Logit Model and Latent Class Model to Analyze Preference Heterogeneity in Choice Experiment Data (선택실험법 자료에서의 선호이질성 분석을 위한 혼합로짓모형 및 잠재계층모형의 활용)

  • Yoo, Byong Kook
    • Environmental and Resource Economics Review
    • /
    • v.21 no.4
    • /
    • pp.921-945
    • /
    • 2012
  • Conditional Logit (CL) model is widely used since its model estimation and interpretation of results of the model is relatively easy, on the other hand, it has the limit of preference heterogeneity of respondents being not fully considered. In this study we used the two models, Mixed Logit (ML) Model and Latent Class Model (LCM) to explain preference heterogeneity of respondents for protection for Boryeong Dam wetland. As a result of the examination for heterogeneity in Boryeong city and six metropolitan areas, we found there was significant difference between two regions. While there was explicit preference heterogeneity within respondents in Boryeong city, we found little heterogeneity within respondents in six metropolitan areas. Thus in the case of six metropolitan areas, CL model can be used for parameter estimation while in the case of Boryeong city, WTP estimates are based on parameter estimates from ML model to reflect the heterogeneity within respondents. Additionally, ML model with interaction and 2-class LCM for respondents in Boryeong city were used to explain the sources of the heterogeneity. The ML model with interaction has advantage of explaining individual unobserved heterogeneity. However The comarison between these two models reflects the fact that LCM provided added information that was not conveyed in the ML model with interaction. Thus, Preference heterogeneity within respondents in this study may be better explained by class level through LCM rather than indiviual level through ML model.

  • PDF