A novel e-commerce customer continuous purchase recommendation model research based on colony clustering
by Qibei Lu; Feipeng Guo
International Journal of Wireless and Mobile Computing (IJWMC), Vol. 11, No. 4, 2016

Abstract: Customer purchasing behaviour in e-commerce platform has become uncertainty and jump affected by the contexts. Existing personalised recommendation models failed to deal with the problem well and they cause loss of customers constantly. This paper puts forward a novel model based on ant colony clustering algorithm to improve customers' continuous purchase intention, including for customer interest is not drift and interest has already shifting. Firstly, for the research field of e-commerce, it gives definition and structured expression to contexts connotation. Secondly, for the problem that growing data sparseness in recommendation system, it introduces ant colony algorithm to cluster similar users in order to reduce the number of candidate neighbour sets and user similarity computing time. Thus, it can improve the target users of nearest neighbour search accuracy. On this basis, according to customer interest variation characteristics, we put forward the dynamic collaborative filtering recommendation algorithm based on Maslow to do adaptive recommend. Finally, the experiment shows effectiveness of this model and the method can solve the problem of e-commerce platform customers' continuous purchase problem.

Online publication date: Thu, 16-Feb-2017

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Wireless and Mobile Computing (IJWMC):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com