The use of Explainable AI (XAI) to improve the accuracy and transparency of production forecasts in the bag manufacturing business is investigated in this study. Historical production data, such as material types, lead times, vendor capacity, and seasonal demand fluctuations, were used to create prediction models with machine learning algorithms. The Gradient Boosting Machines was chosen as the best-performing model. The SHAP (SHapley Additive Explanations) analysis revealed that “Units_Produced” and “Season_Demand” were the most influential elements in predicting demand. XAI substantially increased the model’s transparency, allowing stakeholders to understand the rationale behind forecasts and promoting trust in AI-driven decision making. The findings show the importance of production volume and seasonal modifications in accurate forecasting, resulting in improved inventory management and production planning. This study expands the fields of AI, manufacturing analytics, and production planning by showing the practical benefits of implementing XAI into industrial processes. The inclusion of SHAP analysis allowed for a detailed interpretation of the model’s predictions, revealing that “Units_Produced” and “Season_Demand” were the most influential factors. Limitations include data quality and industry specificity, indicating that future studies should focus on various data sources and broader XAI applications. The findings highlight XAI’s potential to transform production forecasting while improving operational efficiency and strategic planning in manufacturing.