An Improved Switching Hybrid Recommender System Using Naive Bayes Classifier and Collaborative Filtering


Ghazanfar, Mustansar and Prugel-Bennett, Adam (2010) An Improved Switching Hybrid Recommender System Using Naive Bayes Classifier and Collaborative Filtering. In, The 2010 IAENG International Conference on Data Mining and Applications, Hong Kong, 17 - 19 Mar 2010.

Download

[img] PDF
Download (190Kb)

Description/Abstract

Recommender Systems apply machine learning and data mining techniques for filtering un- seen information and can predict whether a user would like a given resource. To date a number of rec- ommendation algorithms have been proposed, where collaborative filtering and content-based filtering are the two most famous and adopted recommendation techniques. Collaborative filtering recommender sys- tems recommend items by identifying other users with similar taste and use their opinions for recom- mendation; whereas content-based recommender sys- tems recommend items based on the content informa- tion of the items. These systems suffer from scalabil- ity, data sparsity, over specialization, and cold-start problems resulting in poor quality recommendations and reduced coverage. Hybrid recommender systems combine individual systems to avoid certain afore- mentioned limitations of these systems. In this paper, we proposed a unique switching hybrid recommenda- tion approach by combining a Naive Bayes classifica- tion approach with the collaborative filtering. Exper- imental results on two different data sets, show that the proposed algorithm is scalable and provide better performance–in terms of accuracy and coverage–than other algorithms while at the same time eliminates some recorded problems with the recommender sys- tems.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Event Dates: 17-19 March, 2010
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science > Comms, Signal Processing & Control
ePrint ID: 268483
Date Deposited: 08 Feb 2010 19:51
Last Modified: 27 Mar 2014 20:15
Contact Email Address: mag208r@ecs.soton.ac.uk
Further Information:Google Scholar
ISI Citation Count:1
URI: http://eprints.soton.ac.uk/id/eprint/268483

Actions (login required)

View Item View Item