In the era of Industry 4.0, mold-making firms face increasing pressure to optimize manufacturing costs while maintaining product quality. This research presents a novel integrated framework combining Monte Carlo Simulation (MCS) and Machine Learning (ML) techniques to address the complexities and uncertainties inherent in injection mold tool manufacturing cost estimation. Our approach leverages MCS to model uncertainties in machine performance, downtime, and material cost fluctuations, while ML algorithms analyze historical and real-time production data to predict machine rates and optimize resource allocation. The integration of these techniques with IoT-enabled sensors provides a dynamic, data-driven framework for real-time cost optimization. The conceptual framework demonstrates potential for significant improvements in cost reduction, machine uptime, and process efficiency. This integrated approach offers a scalable solution for mold-making firms seeking to enhance operational efficiency and profitability in an increasingly competitive market.