Improving Customer Relationship Management based on Intelligent Analysis of User Behavior Patterns

A set of regression, cluster analysis, and association rule mining models, is proposed to search for patterns in user behavior regarding marketing campaigns taking into account user characteristics and financially significant metrics. Using the example of two organizations, it was possible to accurately predict the cost of customer acquisition (CPA, cost-per-action). The use of the models proposed allows organizations to improve advertisement settings to increase online advertising efficiency.