Title: A locality centred recommendation system combining CNM clustering technique with fuzzy preference tree-based ranking algorithm

Authors: Sharon Moses J.; L.D. Dhinesh Babu

Addresses: School of information Technology and Engineering, VIT University, Vellore-632014, Tamil Nadu, India ' School of information Technology and Engineering, VIT University, Vellore-632014, Tamil Nadu, India

Abstract: The internet era has created highly favourable circumstances for business and online services. The need of getting personified recommendations from the increasing pile of information had forced researchers to build recommendation system. In most of the e-commerce websites, recommendation preferences are made by analysing user's behaviour, existing relevant information, browsing patterns, transactional data, item rating and by extracting information from social network profiles. Recommendations predicted from this kind of information can also go futile. Since many of the users gives irrelevant information and many change their views with changing in timely trends. In our work, we are concentrating on generating recommendations based on user's locality. Initially, offline clusterisation is done based on existing location data using CNM-algorithm. The cluster that corresponds to the user request is analysed, and fuzzy preference-based tree is constructed to generate recommendations.

Keywords: user locality; recommendation systems; recommender systems; fuzzy preferences; preference trees; decision support systems; DSS; CNM clustering; Clauset-Newman-Moore; preference ranking; user location.

DOI: 10.1504/IJBIDM.2016.076433

International Journal of Business Intelligence and Data Mining, 2016 Vol.11 No.1, pp.63 - 84

Received: 04 Jan 2016
Accepted: 17 Jan 2016
Published online: 06 May 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article