MACHINE LEARNING BASED CUSTOMER CHURN PREDICTION IN BANKING
Customer connections are of the utmost significance to any bank in the highly competitive industry of banking. The banks view every customer as a lifelong customer. The state in which a client or subscriber ceases engaging in business transactions with a firm or a service provider is referred to as "customer churn". Customer relationship management and business value are improved by customer churn study and forecast. One of the most important aspects of a country's development is the use of AI in the banking industry. The banking industry's growth is largely dependent on its important clients. In order to identify whether a client is worth keeping or at risk of leaving, customer churn analysis is required. From an organizational perspective, acquiring new clients is typically harder or more expensive than keeping the ones you already have. Therefore, predicting customer churn has become common in the banking sector. Commercial banks increase their core competitiveness among rivals while also increasing earnings by lowering client attrition or churn. Although numerous researchers put forth numerous single prediction models and some hybrid models, accuracy is still poor and some algorithms' computation times are still lengthy.