MACHINE LEARNING IN CUSTOMER PROFITABILITY FORECASTING
The aim of this paper is presentation of the model that could be used for the measurement of current and forecasting of the future customer profitability. The purpose of this model is forecasting activities of individual customers in the future, and values that company could expect doing business with them. Modern customer profitability analysis shows that product costs are only one part of the relation enterprise-customer. General framework for defining customer profitability, besides pure financial items, has to include a lot of non-linear and non-financial elements. Machine learning methods can identify and adopt patterns and rules that exist in historical data stored in data bases and/or data warehouses. Proposed model for the forecasting of the customer profitability used two machine learning methods: neural networks and genetic algorithm. The paper shows the ways how proposed methods of machine learning can respond to challenges related to the customer profitability forecasting, at the same time presenting main advantages and disadvantages of their application in that field.