Customer defection prediction in online bookstores

Ya Yueh Shih*, Kwoting Fang, Duen-Ren Liu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Since the cost of retaining an existing customer is lower than that of developing a new one, exploring potential customer defection becomes an important issue in the fiercely competitive environment of electronic commerce. Accordingly, this study used artificial neural networks (ANNs) to predict customers' repurchase intentions and thus avoid defection based on a set of criteria of quality attributes satisfaction and three beliefs in theory of planned behavior (TPB). The predicted repurchase intentions found by utilizing ANNs was compared with traditional analytic tools such as multiple discriminant analysis (MDA). Finally, via T-test analysis indicated that predicted accuracy of ANNs is better in both training and testing phases.

Original languageEnglish
Title of host publicationICEIS 2003 - Proceedings of the 5th International Conference on Enterprise Information Systems
EditorsSlimane Hammoudi, Joaquim Filipe, Olivier Camp, Mario Piattini
PublisherEscola Superior de Tecnologia do Instituto Politecnico de Setubal
Pages352-358
Number of pages7
ISBN (Electronic)9729881618
StatePublished - Apr 2003
Event5th International Conference on Enterprise Information Systems, ICEIS 2003 - Angers, France
Duration: 23 Apr 200326 Apr 2003

Publication series

NameICEIS 2003 - Proceedings of the 5th International Conference on Enterprise Information Systems
Volume2

Conference

Conference5th International Conference on Enterprise Information Systems, ICEIS 2003
Country/TerritoryFrance
CityAngers
Period23/04/0326/04/03

Keywords

  • Artificial neural network (ANNs)
  • Electronic commerce
  • Online shopping
  • Repurchase intention
  • Theory of planned behavior (TPB)

Fingerprint

Dive into the research topics of 'Customer defection prediction in online bookstores'. Together they form a unique fingerprint.

Cite this