Issue |
MATEC Web Conf.
Volume 169, 2018
The Sixth International Multi-Conference on Engineering and Technology Innovation 2017 (IMETI 2017)
|
|
---|---|---|
Article Number | 01003 | |
Number of page(s) | 15 | |
DOI | https://doi.org/10.1051/matecconf/201816901003 | |
Published online | 25 May 2018 |
IPTV program recommendation based on combination strategies
School of Software, Yunnan University, Kunming, China
a Corresponding author: mun2003dhk@gmail.com
As a new interactive service technology, IPTV has been extensively studying in the field of TV pro-gram recommendation, but the sparse of the user-program rating matrix and the cold-start problem is a bottleneck that the program recommended accurately. In this paper, a flexible combination of two recommendation strategies proposed, which explored the sparse and cold-start problem as well as the issue of user interest change over time. This paper achieved content-based filtering section and collaborative filtering section according to the two combination strategies, which effectively solved the cold-start program and over the sparse problem and the problem of users interest change over time. The experimental results showed that this combinational recommendation system in optimal parameters compared by using any one of two combination strategies or not using any combination strategy at all, and the reducing range of MAE is [2.7%,3%].The increasing range of precision and recall is [13.8%95.5%] and [0,97.8%], respectively. The experiment showed better results when using combinational recommendation system in optimal parameters than using each combination strategies individually or not using any combination strategy.
© The Authors, published by EDP Sciences, 2018
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (http://creativecommons.org/licenses/by/4.0/).
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.