Using a Critic to Promote Less Popular Candidates in a People-to-People Recommender System
نویسندگان
چکیده
This paper shows how to improve the recommendations of an interaction-based collaborative filtering (IBCF) recommender used in online dating. Previous work has shown that IBCF works well in this domain, although it tends to rank popular candidates highly, which leads to these users receiving a large number of contacts. We address this problem by using a Decision Tree model as a “critic” to re-rank the candidates generated by IBCF, effectively promoting less popular candidates. This method was first evaluated on historical data from a large online dating site and then trialled live on the same site by providing recommendations to a large number of users throughout a 9 week period. The live trial confirmed the consistency of the analysis on historical data and the ability of the method to generate suitable candidates over an extended period. Our recommendations gave higher success rates than those for a control group made with a baseline recommender.
منابع مشابه
Collaborative Filtering for people-to-people recommendation in online dating: Data analysis and user trial
A common perception is that online dating systems “match” people on the basis of profiles containing demographic and psychographic information and/or user interests. In contrast, product recommender systems are typically based on Collaborative Filtering, suggesting purchases not based on “content” but on the purchases of “similar” users. In this paper, we study Collaborative Filtering for peopl...
متن کاملCSCW 2000 Report
I attended the tutorial, “Recommender Systems: Collaborating in Commerce and Communities” at this year’s CSCW conference. Recommender systems attempt to alleviate the problem of information overload. There are too many books, journal articles, news articles, etc. for us to sift through. Recommender systems address this problem by recommending things that are “worthwhile”. There are many approac...
متن کاملMechanism to Promote Student Participation in the University Management System with Emphasis on the Development of Cultural Components
In Iranian higher education, the university management system (UMS) has taken on an overly pyramidal and centralized structure and has created a minimal intervention space for stakeholders, especially students which have challenged some of the functional areas of universities. This research shows the lack of proper development of participatory culture in universities as one of the main reasons....
متن کاملAn Effective Algorithm in a Recommender System Based on a Combination of Imperialist Competitive and Firey Algorithms
With the rapid expansion of the information on the Internet, recommender systems play an important role in terms of trade and research. Recommender systems try to guess the user's way of thinking, using the in-formation of user's behavior or similar users and their views, to discover and then propose a product which is the most appropriate and closest product of user's interest. In the past dec...
متن کاملسیستم پیشنهاد دهنده زمینهآگاه برای انتخاب گوشی تلفن همراه با ترکیب روشهای تصمیمگیری جبرانی و غیرجبرانی
Recommender systems suggest proper items to customers based on their preferences and needs. Needed time to search is reduced and the quality of customer’s choice is increased using recommender systems. The context information like time, location and user behaviors can enhance the quality of recommendations and customer satisfication in such systems. In this paper a context aware recommender sys...
متن کامل