Poor packaging can definitely contribute to food spoilage, reducing food quality and shelf life. Active packaging using edible biofilm with antimicrobial essential oils can inhibit microbial growth and extend product freshness. The purpose of this study was to classify edible biofilm products to determine their quality and predict proper drying conditions. The method involved system modeling using Unified Modeling Language (UML) and Business Process Model and Notation (BPMN) to map the production process from raw material handling to industrial scale manufacturing. Subsequently, machine learning models were applied: the Decision Tree model for classifying product quality including physical, mechanical, and antimicrobial properties and Ordinary Least Squares (OLS) linear regression for predicting drying parameters. The research steps consisted of creating system models to improve clarity and team alignment, collecting relevant data on elongation, tensile strength, moisture content, and antimicrobial activity, then applying the Decision Tree for quality classification and antimicrobial categorization into four levels. OLS regression was used to model the relationship between drying conditions and final moisture content. Results demonstrated that UML and BPMN modeling enhanced understanding and consistency in production flow. The Decision Tree classified edible biofilm quality into three categories with 80.5% accuracy and antimicrobial ability into four inhibitory levels with 95% accuracy. The OLS regression predicted drying outcomes with 64% explanatory power and statistical significance (p-value < 0.05). This study contributes to intelligent packaging development by integrating system modeling and machine learning, enabling early classification a nd drying prediction to improve quality control, efficiency, and reliability in active food packaging. Keywords: antrimicobe, decision tree, edible biofilm, linear regression, use case