AN INTRODUCTION TO FACTORIZATION TECHNIQUE FOR BUILDING RECOMMENDATION SYSTEMS

Nguyen Thai Nghe

Tóm tắt


Recommender System (RS) is successfully applied in predicting user preferences. For instance, RS has been used in many areas such as in e-commerce (for online shopping), in entertainments (music/movie/video clip... recommendation), and in education (learning resource recommendation). In Vietnam, e-commerce is initially growing, thus, RS may be an interesting and potential research topic in the next years. In this work, we shortly introduce about the RS and thoroughly describe one of the prominent techniques in RS which is Matrix Factorization (MF). We describe the MF in details so that the new reader can understand and implement it easily. In the experiments, we set up and compare the MF with other techniques using three data sets from two different areas which are entertainment and education. Experimental results show that the MF can work well in both entertainment (e-commerce) and education domain.

Từ khóa


Recommender Systems; Rating prediction; Matrix factorization



DOI: http://dx.doi.org/10.37569/DalatUniversity.3.2.249(2013)

Các bài báo tham chiếu

  • Hiện tại không có bài báo tham chiếu.


Copyright (c) 2013 Nguyen Thai Nghe

Creative Commons License
Công trình này được cấp phép theo Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Văn phòng Tạp chí Đại học Đà Lạt
Nhà A25 - Số 1 Phù Đổng Thiên Vương, Đà Lạt, Lâm Đồng
Email: tapchikhoahoc@dlu.edu.vn - Điện thoại: (+84) 263 3 555 131

Creative Commons License
Trên nền tảng Open Journal Systems
Thực hiện bởi Khoa Công nghệ Thông tin