Simulation research of university library recommended system based on big data and data mining

DOI

10.2991/icmmita-15.2015.40How to use a DOI?

Keywords

University library; recommendation system; information visualization; data mining

Abstract

This paper based on the specific needs of the university library, analyzes construct necessity, feasibility and technical solutions to select automatic recommendation system for books, and a brief introduction of collaborative filtering algorithms, in particular the correlation calculation and different evaluation criteria. Then nearly 5 million loan offline test history data validate our ideas through the use of the university library, and focused on the specific needs due to the university library, the recommended herein may be based on local search for similar user, saves computing resources and at the same time without sacrificing significant accuracy. Finally, we have also introduced some of the content related to the implementation, including the consideration of a cold start and user interaction design, and lack of presence through the implementation of current research findings. This article provides some practical guidance and reference value for the field of application of the recommendation system of university library.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Rui Li
PY  - 2015/11
DA  - 2015/11
TI  - Simulation research of university library recommended system based on big data and data mining
BT  - Proceedings of the 2015 3rd International Conference on Machinery, Materials and Information Technology Applications
PB  - Atlantis Press
SP  - 202
EP  - 206
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmita-15.2015.40
DO  - 10.2991/icmmita-15.2015.40
ID  - Li2015/11
ER  -