Abstract

Database Marketing is a requisite and efficient weapon for firms to put one-to-one relationship marketing in practice. The major task of this practice is to evaluate or calculate individual customer value through proper analyses of customers' purchase history data. Conventional approaches to measuring customer value mainly focus on the average value from past to present, lacking the dynamic viewpoints. What firms need to do is to be able to capture the migration patterns of a customer's value in advance, in order to explore potential customers and prevent inactive customers. This paper employs the Markov chain model and the hierarchical Bayesian approach to construct individual customer's transition probability matrix for forecasting the customer value migration process.