A model for predicting customer value from perspectives of product attractiveness and marketing strategy

S. L. Chan, W. H. Ip, Wing Sing Cho

Research output: Journal article publicationJournal articleAcademic researchpeer-review

36 Citations (Scopus)


This paper proposes a model for customer relationship management (CRM) using iThink®, which incorporates the concept of system dynamics. The proposed CRM model consists of module 1: a customer purchasing behavior model, module 2: a Markov chain model, and module 3: a financial returns model. By considering the marketing activities and product attractiveness to the customer, the probability that a customer will (re)purchase can be modeled in module 1. The probabilities are then fitted into module 2 for the calculation of customer lifetime value (CLV). The estimated CLV for each customer is inputted into module 3 to predict the firm's return on investment in the long term. By defining the parameters on the attractiveness of a product and on user responses from historical marketing campaigns, a firm can easily evaluate its business strategy from both marketing and product development perspectives, thereby refining those parameters and adopting the best strategy for creating customer value and yielding the maximum profit. A case study of a listed firm in Hong Kong is employed to illustrate our model, which not only gives insights into the product development, but can also support the decisions related to marketing activities.
Original languageEnglish
Pages (from-to)1207-1215
Number of pages9
JournalExpert Systems with Applications
Issue number2
Publication statusPublished - 1 Mar 2010


  • Customer lifetime value
  • Customer relationship management
  • Markov chain model
  • System dynamics

ASJC Scopus subject areas

  • General Engineering
  • Computer Science Applications
  • Artificial Intelligence


Dive into the research topics of 'A model for predicting customer value from perspectives of product attractiveness and marketing strategy'. Together they form a unique fingerprint.

Cite this