Customer interest classification method of e-commerce trading platform based on decision tree algorithm
by Xiaowei Ma; Xin Yao; Shizhong Guo
International Journal of Networking and Virtual Organisations (IJNVO), Vol. 29, No. 3/4, 2023

Abstract: Due to the large number of customers and diverse interest characteristics in e-commerce trading platforms, there are many problems such as large classification errors, low accuracy in customer interest feature extraction, and high classification time cost. A decision tree algorithm-based customer interest classification method for e-commerce trading platforms is proposed. Based on the basic structure of e-commerce transaction platform web pages, non-target nodes and target nodes are removed, and the DFSD fusion method is introduced to extract web browsing content. Then, multi-dimensionally annotate the key interest information and extract customer interest features through multimodal feature fusion. Build a customer interest tree for e-commerce trading platforms, with the customer interest feature data being processed by calculating its entropy value, calculating the information gain of leaf nodes, and building a decision tree classification model based on specific classification rules. Experimental results show that this method reduces classification errors and has good classification results.

Online publication date: Wed, 10-Jan-2024

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 Networking and Virtual Organisations (IJNVO):
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