• Journal of KIISE:Software and Applications
• /
• v.32 no.9
• /
• pp.901-911
• /
• 2005

With the development of e-commerce and the proliferation of easily accessible information, information filtering has become a popular technique to prune large information spaces so that users are directed toward those items that best meet their needs and preferences. While many collaborative filtering systems have succeeded in capturing the similarities among users or items based on ratings to provide good recommendations, there are still some challenges for them to be more efficient, especially the user bias problem, non-transitive association problem and cold start problem. Those three problems impede us to capture more accurate similarities among users or items. In this paper, we provide probabilistic model approaches for UCHM and ICHM which are suggested to solve the addressed problems in hopes of achieving better performance. In this probabilistic model, objects (users or items) are classified into groups and predictions are made for users considering the Gaussian distribution of user ratings. Experiments on a real-word data set illustrate that our proposed approach is comparable with others.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2005.05a
• /
• pp.629-638
• /
• 2005

In this paper, we consider two issues in collaborative filtering, which are closely related with the number of ratings of a user. First issue is the relationship between the number of ratings of a user and the performance of collaborative filtering. The relationship is investigated with two datasets, EachMovie and Movielens datasets. The number of ratings of a user is critical when the number of ratings is small, but after the number is over a certain threshold, its influence on recommendation performance becomes smaller. We also provide an explanation on the relationship between the number of ratings of a user and the performance in terms of neighborhood formations in collaborative filtering. The second issue is how to select an initial product list for new users for gaining user responses. We suggest and analyze 14 selection strategies which include popularity, favorite, clustering, genre, and entropy methods. Popularity methods are adequate for getting higher number of ratings from users, and favorite methods are good for higher average preference ratings of users.

• The KIPS Transactions:PartD
• /
• v.15D no.3
• /
• pp.421-428
• /
• 2008

Collaborative filtering is a popular technique used for the recommendation system, but its performance, especially the accuracy of recommendation, depends on how to define the reference group. This paper proposes a new contents recommendation scheme based on collaborative filtering technique whose reference groups are created by consumer's affection and consumption type in order to improve the accuracy of recommendation. In this paper, joy, sadness, anger, happiness, and relax are considered as the consumer's affection. And, low-utility / low-pleasure, low-utility / high-pleasure, high-utility / low-pleasure, and high-utility / high-pleasure are considered as the consumer's shopping types. Experimental results show that the proposed scheme improves the accuracy of recommendation compared to the recommendation scheme considering neither consumer's affection nor consumption type.

• 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.

• Journal of KIISE
• /
• v.44 no.6
• /
• pp.621-627
• /
• 2017

Collaborative filtering is a technique that effectively recommends unrated items for users. Collaborative filtering is based on the similarity of the items evaluated by users. The existing top-N recommendation methods are based on pair-wise and list-wise preference models. However, these methods do not effectively represent the relative preference of items that are evaluated by users, and can not reflect the importance of each item. In this paper, we propose a new method to represent user's latent preference by combining an existing preference model and the notion of inverse user frequency. The proposed method improves the accuracy of existing methods by up to two times.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.7
• /
• pp.768-774
• /
• 2016

This paper deals with a method to recommend the combination of items as a group according to similarity to handle application area such as fashion and cooking, while the previous methods recommend single item such as a book, music or movie. Collaborative filtering is a method to recommend an item selected by users with similar tendency based on similarity between users. In this paper, the proposed method generates a set of frequent items based on collaborative filtering and association rules and recommends a group by similarity between groups. To show the validity of the proposed method, experiments are performed with purchase data collected from e-commerce for four months.

• The Journal of Society for e-Business Studies
• /
• v.14 no.1
• /
• pp.1-11
• /
• 2009

Many neighbors are needed for making the recommendation quality better and stable in collaborative filtering. Furthermore, the quality is not so good mainly due to a reason that high similarity between two users does not guarantee the same preference to items considered for recommendation. Dissimilar users who have consistency in item selection can be useful for predicting preferences. This paper proposes a new collaborative filtering method, defining trust based on consistency for improving this phenomenon. Empirical studies show that such a method reduces the number of neighbors required to make the recommendation quality stable and the recommendation quality itself is also significantly improved.

• The Journal of Korean Association of Computer Education
• /
• v.21 no.5
• /
• pp.61-68
• /
• 2018

Collaborative filtering is a fundamental technique implemented in many commercial recommender systems and provides a successful service to online users. This technique recommends items by referring to other users who have similar rating records to the current user. Hence, similarity measures critically affect the system performance. This study addresses problems of previous similarity measures and suggests a new similarity measure. The proposed measure reflects the subjectivity or vagueness of user ratings and the users' rating behavior by using fuzzy logic. We conduct experimental studies for performance evaluation, whose results show that the proposed measure demonstrates outstanding performance improvements in terms of prediction accuracy and recommendation accuracy.

• The Journal of Korean Association of Computer Education
• /
• v.19 no.1
• /
• pp.111-118
• /
• 2016

Measuring similarity in collaborative filtering-based recommender systems greatly affects system performance. This is because items are recommended from other similar users. In order to overcome the biggest problem of traditional similarity measures, i.e., data sparsity problem, this study suggests a new similarity measure that is the optimal combination of previous similarity and the value reflecting the number of co-rated items. We conducted experiments with various conditions to evaluate performance of the proposed measure. As a result, the proposed measure yielded much better performance than previous ones in terms of prediction qualities, specifically the maximum of about 7% improvement over the traditional Pearson correlation and about 4% over the cosine similarity.

• The Journal of Korean Association of Computer Education
• /
• v.14 no.5
• /
• pp.97-104
• /
• 2011

Collaborative filtering is a methodology to recommend websites by obtaining data and opinions from the other users with similar tastes. During the past few years, this method has been used in various fields such as books, food, and movies in e-commerce systems. This study addresses the computation of similarity between users to determine items to be recommended in collaborative filtering systems. Previous studies measured similarity between users by treating each user's ratings independently without considering the distribution of the user's ratings. In contrast, this study measures similarity by utilizing position and rank information of each rating in the range of the user's ratings. The result of the experiments on the real datasets demonstrated that the proposed method improves the mean absolute error significantly, compared to the previous methods, especially when the predetermined range of ratings is large.