Recommendation Sys

Only available on StudyMode
  • Topic: Information retrieval, Recommender system, Cold start
  • Pages : 74 (18221 words )
  • Download(s) : 187
  • Published : February 24, 2013
Open Document
Text Preview
Design and Evaluation of a Recommender System

INF-3981 Master’s Thesis in Computer Science

Magnus Mortensen

Faculty of Science Department of Computer Science University of Tromsø

February 5, 2007

Design and Evaluation of a Recommender System

INF-3981 Master’s Thesis in Computer Science

Magnus Mortensen

Faculty of Science Department of Computer Science University of Tromsø

February 5, 2007

Abstract

In the recent years, the Web has undergone a tremendous growth regarding both content and users. This has lead to an information overload problem in which people are finding it increasingly difficult to locate the right information at the right time. Recommender systems have been developed to address this problem, by guiding users through the big ocean of information. Until now, recommender systems have been extensively used within e-commerce and communities where items like movies, music and articles are recommended. More recently, recommender systems have been deployed in online music players, recommending music that the users probably will like. This thesis will present the design, implementation, testing and evaluation of a recommender system within the music domain, where three different approaches for producing recommendations are utilized. Testing each approach is done by first conducting live user experiments and then measure recommender precision using offline analysis. Our results show that the functionality of the recommender system is satisfactory, and that recommender precision differs for the three filtering approaches.

v

Acknowledgments

The author would like to thank his supervisor, Professor Dag Johansen, for valuable ideas, support and motivation. Many thanks to the test users. The experiment would not be possible without your help. Thanks to ˚ge Kvalnes for server support. A Thanks to the rest of the WAIF team for providing valuable input. Also thanks to FAST Search & Transfer, in particular represented by Krister Mikalsen, for helpful discussions. Finally, thanks to girlfriend Ragnhild Høifødt for reading through the draft and providing support.

vii

Contents

Abstract Acknowledgments Contents 1 Introduction 1.1 Background . . . . . . 1.2 Problem definition . . 1.3 Interpretation . . . . . 1.4 Method and approach 1.5 Outline . . . . . . . .

iii v i 1 1 2 2 2 3 5 5 7 8 9 10 12 16 17 17 17 19 20 20 20 21 21 22

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

. . . . .

2 Related work 2.1 The World Wide Web . . . . . . . . . . . 2.2 Information retrieval and filtering . . . . . 2.3 Recommender systems . . . . . . . . . . . 2.3.1 Content-based filtering . . . . . . . 2.3.2 Collaborative filtering . . . . . . . 2.3.3 Collaborative filtering approaches . 2.3.4 Hybrid approach . . . . . . . . . . 2.4 Improving recommender systems . . . . . 2.4.1 Intrusiveness . . . . . . . . . . . . 2.4.2 Contextual information . . . . . . 2.4.3 Evaluating recommender systems . 2.4.4 Other improvements . . . . . . . . 2.5 Case study: Pandora vs. Last.fm . . . . . 2.5.1 Exploring new artists . . . . . . . 2.5.2 Overspecialization . . . . . . . . . 2.5.3 Conclusion . . . . . . . . . . . . . 2.6 Summary . . . . . . . . . . . . . . . . . .

. . . . . . . . . . . . . . . . .

. . . . . . . . . . . . . . . . .

. . . . . . . . . . . . . . . . .

. . . . . . . . . . . . . . . . .

. . . . . . . . . . . . . . . . .

. . . . . . . . . . . . . . . . .

. . . . . . . . . . . . . . . . .

. . . . . . . . . . . . . . . . .

. . . . . . . . . . . . . . . . .

. . . . . . . . . . . . . . . . .

. . . . . . . . . . . . . . . . .

. . . . . . . . . . . . . . . . .

....
tracking img