In the healthcare sector, especially within hospitals, efficient nurse allocation is critical for maintaining patient care quality, reducing waiting times, and optimizing resources, especially in settings with high patient inflow and limited staff. This work focuses on developing a Genetic Algorithm (GA)-based optimization model to improve nurse allocation in real-time based on varying patient acuity scores, nurse competency levels, and daily shifts, while adhering to constraints commonly present in hospital environments. Specifically, the model addresses complex constraints, such as the limited number of available nurses, a three-shift structure, a maximum allowable 8-h shift per nurse, and patient acuity scores, which represent the severity and immediacy of care required by each patient. These constraints help ensure that nurses with appropriate competencies are assigned to patients whose care needs align with the nurses skill levels. Model can be adapted to real-time data inputs, making it responsive to fluctuating daily requirements. By incorporating the actual acuity scores and competency data from a hospital. The model allows for a practical and robust testing environment, adding real-world relevance and accuracy to the outcomes. In real-time application, the model could dynamically adjust shift assignments based on incoming patient data, enhancing both patient outcomes and nurse workload management. Expected benefits include improved alignment between patient care needs and nurse skill sets, more balanced nurse workloads, reduced stress and burnout among nursing staff, and overall higher quality of patient care.