Optimizing Staffing Level and Waiting Time Using Queuing Model in Bank Service

Long waiting times in banking services reduce customer satisfaction and operational efficiency, often resulting from misaligned staffing levels and fluctuating client traffic. The Cooperative Bank of Oromia in Holeta, Ethiopia, experiences significant service delays due to staffing inefficiencies and unpredictable customer arrivals. This study is aimed at optimizing staffing arrangements and minimize customer-waiting times to improve service delivery. Long short-term memory (LSTM) neural network was used to predict customer foot traffic, regression analysis assessed the impact of staffing on waiting times, and the M/M/C queuing model determined optimal staffing levels. Optimal staffing was identified as seven servers for the Holeta branch and six servers for the Goro Qeransa branch, with average system occupancy of 5.34 and 6.69 customers, respectively, leading to reduced waiting times. Aligning staffing with predicted customer flows can substantially improve service efficiency and customer satisfaction. Bank management should adopt data-driven staffing strategies based on predictive forecasting and queuing models, which can also be adapted for similar banking contexts beyond Ethiopia.