This paper introduces a bagging-based machine learning model designed for predicting individual dietary preferences, particularly focusing on the impact of age. Understanding dietary preferences across different age groups is essential for offering personalized nutrition recommendations, as these preferences can vary significantly throughout life. The model employs bagging, an ensemble learning technique that combines diverse base learners to improve prediction accuracy and resilience. Utilizing a comprehensive dataset containing various dietary habits, detailed nutritional profiles, and key demographic indicators, the study extensively engages in feature engineering and model optimization, with particular attention to age-related factors. The model’s precision and comprehensiveness significantly enhance personalized dietary guidance. Importantly, a comparative analysis demonstrates the consistent outperformance of the bagging model over other popular models, including XGBoost, AdaBoost, Markov Models, and Gradient Boost, indicating its superior performance in predicting dietary preferences based on age. Incorporating age-related features into the model provides deeper insights into how age influences dietary preferences and nutritional needs. The study highlights the need for tailored model selection and advanced feature techniques for food subcategories.This research contributes to personalized healthcare by predicting age-related dietary preferences, facilitating tailored nutrition recommendations for specific age groups.