Customer Clustering Based on RFM Model and Using Fractal Algorithm

One of the most important aspects of customer relationship management is discovering the customer's purchasing behavior pattern. The organization can act by defining more precise marketing strategies to attract similar customers. In today's competitive world, accurate knowledge of customers and the ability to respond to their needs is critical to the success of organizations. With recent advances in data mining and big data analysis, organizations are now able to use more sophisticated methods to segment customers and better understand their behavior. The novelty, frequency and financial model (RFM) as one of the prominent models in this field, provides the possibility of dividing customers based on their value for the organization. In this thesis, a customer segmentation scheme is presented using fractal clustering and AVOAGA optimization method, which is a combination of two optimization methods, African vulture and genetic method. The simulation of the proposed design was done in the Python environment and using the standard data set containing RFM of customers. Based on the results obtained from the simulation, the proposed design is improved in both compactness and dispersion indices compared to the basic design.