Personalized Canine Diet Generation Using Machine Learning and Constraint Optimization

The growing demand for customized pet diets highlights the shortcomings of commercial dog foods designed for all breeds, especially when it comes to addressing breed-specific diseases, metabolic disorders, and health risks. This research presents the development and evaluation of a hybrid system for formulating wet canine food recipes. The system combines data on ingredients, veterinary feeds, and breed-related diseases; the architecture includes a recommendation module for ingredient selection and a linear programming block for recipe optimization, considering veterinary nutrient restrictions. The evaluation of the system included automatic classification of foods by specialization, visual analysis of recipe clustering, and comparison of formulas obtained by different models. The average precision of label recovery was 85.4% for TF-IDF and 88.2% for the E5 model. A comparison of ingredient extraction methods showed that machine learning produces more stable recipes, while the statistical approach provides greater variability. The developed system demonstrates potential for automating recipe creation, filling in missing data, and developing veterinary decision support platforms aimed at personalized diet selection based on the physiological needs of animals.