Badrul Munir Sarwar

Item-based collaborative filtering recommendation algorithms

Recommender systems apply knowledge discovery techniques to the problem of making personalized recommendations for information, products or services during a live interaction. These systems, especially the k-nearest neighbor collaborative ltering based ones, are achieving widespread success on the Web. The tremendous growth in the amount of available information and the number of visitors to Web sites in recent years poses some key challenges for recommender systems. These are: producing high quality recommendations, performing many recommendations per second for millions of users and items and achieving high coverage in the face of data sparsity. In traditional collaborative ltering systems the amount of work increases with the number of participants in the system. New recommender system technologies are needed that can quickly produce high quality recommendations, even for very large-scale problems. To address these issues we have explored item-based collaborative ltering techniques. Item-based techniques rst analyze the user-item matrix to identify relationships between di erent items, and then use these relationships to indirectly compute recommendations for users. In this paper we analyze di erent item-based recommendation generation algorithms. We look into di erent techniques for computing item-item similarities (e.g., item-item correlation vs. cosine similarities between item vectors) and di erent techniques for obtaining recommendations from them (e.g., weighted sum vs. regression model). Finally, we experimentally evaluate our results and compare them to the basic k-nearest neighbor approach. Our experiments suggest that item-based algorithms provide dramatically better performance than user-based algorithms, while at the same time providing better quality than the best available userbased algorithms.

Analysis of recommendation algorithms for e-commerce

ABSTRACT Re ommender systems apply statisti al and knowledge disovery te hniques to the problem of making produ t re ommendations during a live ustomer intera tion and they are a hieving widespread su ess in E-Commer e nowadays. In this paper, we investigate several te hniques for analyzing large-s ale pur hase and preferen e data for the purpose of produ ing useful re ommendations to ustomers. In parti ular, we apply a olle tion of algorithms su h as traditional data mining, nearest-neighbor ollaborative ltering, and dimensionality redu tion on two di erent data sets. The rst data set was derived from the web-pur hasing transa tion of a large Eommer e ompany whereas the se ond data set was olle ted from MovieLens movie re ommendation site. For the experimental purpose, we divide the re ommendation generation pro ess into three sub pro esses{ representation of input data, neighborhood formation, and re ommendation generation. We devise di erent te hniques for di erent sub pro esses and apply their ombinations on our data sets to ompare for re ommendation quality and performan e.

Using filtering agents to improve prediction quality in the GroupLens research collaborative filtering system

Collaborative filtering systems help address information overload by using the opinions of users in a community to make personal recommendations for documents to each user. Many collaborative filtering systems have few user opinions relative to the large number of documents available. This sparsity problem can reduce the utility of the filtering system by reducing the number of documents for which the system can make recommendations and adversely affecting the quality of recommendations. This paper defines and implements a model for integrating content-based ratings into a collaborative filtering system. The filterbot model allows collaborative filtering systems to address sparsity by tapping the strength of content filtering techniques. We identify and evaluate metrics for assessing the effectiveness of filterbots specifically, and filtering system enhancements in general. Finally, we experimentally validate the filterbot approach by showing that even simple filterbots such as spell checking can increase the utility for users of sparsely populated collaborative filtering systems.