Real-time production scheduling optimized through data-driven approaches offers significant potential to improve manufacturing efficiency and responsiveness. This study presents the development and validation of an intelligent scheduling model tailored to the smart yogurt manufacturing process at Kefalos Cheese Pvt Ltd, Zimbabwe. The model's novelty resides in benchmarking its performance against other leading African and global dairy manufacturers, demonstrating its capability for scalable adoption and competitiveness beyond local boundaries. The scheduling KPIs also include energy efficiency and wastage reduction measures, supporting sustainable practice integration. Leveraging real-time operational data, the model integrates key factors, including machine utilization, changeover time, demand variability, and batch size, through a MATLAB/Simulink implementation. A Taguchi experimental design is used to systematically analyze factor effects on scheduling Key Performance Indicators (KPIs), and a quadratic regression model predicts schedule performance under different operational scenarios. Results indicate optimal scheduling when machine utilization is balanced at 75-90%, changeover times are minimized, and demand variability is controlled, enhancing both throughput and schedule robustness. The study proposes a practical implementation framework incorporating data acquisition through OPC UA protocols and adaptive feedback loops, supporting scalable adoption in Zimbabwe's dairy manufacturing sector. This research underscores the value of integrating smart factory concepts with robust scheduling models to tackle dynamic production challenges in perishable, multi-product environments.