Building an online purchasing behavior analytical system with neural network

Mo Wang, S. J. Rees, S. Y. Liao

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

9 Citations (Scopus)

Abstract

A back-propagation neural network (BPNN) classification model based on the data mining process procedures to analyze online customer behavior was presented. It was demonstrated that BPNN performs very well against two traditional statistical classification technologies which are K-means clustering and multiple discriminate analysis (MDA) on real-world data sets. The reliability and validity of the BPNN system were tested by comparing their classification ability with two different data sets which include an external statistical data set and an online survey data set. The results showed that the BPNN classification model has a higher classification accuracy and robustness than the alternatives used.
Original languageEnglish
Title of host publicationData Mining III
Pages225-237
Publication statusPublished - 2002
EventThird International Conference on Data Mining, Data Mining III - Bologna, Italy
Duration: 25 Sept 200227 Sept 2002

Publication series

NameManagement Information Systems
Volume6

Conference

ConferenceThird International Conference on Data Mining, Data Mining III
Country/TerritoryItaly
CityBologna
Period25/09/0227/09/02

Fingerprint

Dive into the research topics of 'Building an online purchasing behavior analytical system with neural network'. Together they form a unique fingerprint.

Cite this