Thesis:

Predicting customer churn in e-banking using data mining and Genetic Algorithm

As technology advances, services increase and it is difficult for a company to predict which customers are likely to leave their services. In the telecommunications industry, dropout prediction is a problem that has been the focus of various researchers in recent years. Anticipating churn for a company is a very tiring task and like many companies and upcoming startups, there is a tough competition in the market to retain customers by providing services that are beneficial to both parties. It is very difficult to predict the real customers of the company. The use of data mining techniques to predict customer churn is new in the field of electronic banking. Data collection and feature selection to predict customer churn in the field of electronic banking services is one of the new aspects of this research. It is expected that the bank managers will consider strategies to prevent the leakage with a better understanding of the leakage characteristics. These strategies should be used for customers whose characteristics are more similar to the attrition groups identified above. In this research, the CRISP method is used to predict customer attrition in ?

Keywords: electronic banking services. The purpose of this research is to identify the characteristics of chur