|
Author(s): Mo Wang, S J Rees & S Y Liao
Abstract:
With the rapid growth of the worldwide online sales, it is very important to analyze the factors influencing online purchasing behaviors.
The analysis of the data on online customers has not been given adequate effort.
The difficulty of accurate assessment of online customer behaviors is due to its complexity, disorganized knowledge about it, and the lack of effective and valid tools to measure and predict it.
The technology of data mining has provided the opportunity to extract interesting knowledge from large amount of data.
Since the back-propagation neural network (BPNN) is one of the most powerful general nonlinear modeling techniques, we have built a back office analytical system based on it and returned our classification and prediction results back to the consumer.
The purpose of the research is to develop a system to help better understand customer online purchasing behaviors and to assist the customer relationship management campaigns of e-business enterprises.
The system aims to classify online customers and predict their purchasing behaviors according to their demographics and attitudes toward online shopping.
The data used for model building and testing was collected through a website.
A group of students at City University of Hong Kong participated in the data collection process to provide their online shopping behaviors.
To evaluate the performance of the proposed system, we compare it with other mature classification tools, namely, K-means clustering and multiple discriminate analysis (MDA) tools.
The results show better precision with the designed system.
...
Size: 747 kb
Paper DOI: 10.2495/DATA020241
|
|
Download
the Full Article
Price: US$
0.00
This article is part of the WIT OpenView scheme and you can download the full text Adobe PDF article for FREE by clicking the 'Openview' icon below.
 Send
this page to a colleague.
|
Home
Follow WIT Press
WIT Press on Twitter
Wessex Institute of Technology on Blogspot
