Workload estimation with machine learning algorithms in banking

The digitalizing world is causing radical changes, especially in the financial sector. The increase in the number of digital banks in recent years has emerged as both a threat and a warning for traditional branch banks on the path to digitalization. In this new era, it is of great importance for branch banks to be able to manage large cost items such as personnel expenses in order to gain an advantage in competition with digital banks. Digital banks have the advantage of attracting customers with their low operational costs and fast service delivery. Therefore, in order for branch banks to maintain their share in the sector and achieve sustainable growth, they need to adopt digitalization and carry out their staff planning effectively. Optimization of the number of staff is a critical factor that can directly affect both employee satisfaction and customer experience. Reducing the number of staff can increase the workload of employees, reduce their satisfaction and lead to longer customer waiting times. Determining excessive staff can increase costs with unused capacity and negatively affect the social lives of employees due to possible relocations. Therefore, banks need to both reduce costs and increase service quality by determining the optimal number of staff. This study aims to explore the potential advantages of artificial intelligence techniques in the staff planning and resource management processes of a bank branch operating in the financial sector. A specific title group was analyzed in detail using different methods, and past performance data, customer demands, and other factors were analyzed. These data were used to accurately predict future workloads. Within the scope of the study, it was observed that the Extreme Gradient Boosting (XGBoost) method had the most effective results with high correlation values ​​of 0.99 and 0.91 obtained. This method enables banks to optimize costs and maximize customer and employee satisfaction by making more effective staff planning. As a result, this research offers an innovative approach to increasing resource management and operational efficiency in the banking sector by deeply examining the role of artificial intelligence in staff planning. It is emphasized that banks need to develop more efficient and effective strategies using technologies in order to compete in the digital world. In this context, it can be stated that artificial intelligence-based staff planning models are an important tool for banks to both reduce their costs and increase service quality.