Presenting a Model for Calculating ISACO Customers Lifetime Value by Markov Chain using data mining techniques

Abstract

One of the key issues in the studies on customer relationship management (CRM) and modalities of marketing budget allocation is to calculate the customer’s lifetime value and applying it to macro-management decisions. A major challenge in this sector pertains to making calculations so as to incorporate the possibility of changes in the behavior of customers with the turn of time in the model. In this article, we first classify the customers of ISACO using clustering techniques and use multilayer neural network to calculate the monetary value of each group of customers during the specific period of time. Then, we use the Markov chain approach to develop a model for calculating the lifetime value of ISACO’s customers by taking into consideration the possibility of changes in their behavior in future time periods. In this study, a new approach has been used to estimate the parameters of the model proposed for calculating the future lifetime value of ISACO’s customers. This method takes into consideration the possibility of changes in the customer behavior throughout their interaction with the company. The results obtained here may be used in the allocation of marketing budget and adoption of macro-management decisions to envisage various projects for customers with different lifetime value.

Keywords

• customer lifetime value
• future value
• isaco
• markov chain
• clustering
• neural network