Production Decision Making Problem Based on Bayesian Estimation with 0-1 Planning Models

Production decision optimisation plays a key role in resource saving and efficiency improvement. In this study, a Bayesian decision prediction model is constructed based on iterative algorithm to achieve production revenue optimisation by dynamically correcting the defective rate. Simulation experiments show that the model obtains 9695.1 yuan,12891 yuan,13658.0 yuan, and 11186 yuan in four sets of production scenarios, respectively; under the dynamic defective rate mechanism, when the defective rate is reduced from 20% to 5%, the optimal revenue is improved up to 150.93% with the same number of decisions. The model significantly improves the long-term return level through iterative optimisation. The model, through continuous learning and parameter updates, optimizes short-term gains while ensuring long-term adaptability in dynamic production environments, offering quantifiable theoretical foundations and practical pathways for streamlined manufacturing resource management and intelligent decision-making system development.