An Optimized Framework for Personalized Meal Planning using MCDM and the Honey Badger Algorithm

This project introduces a personalized meal planner system that uses dietary preferences to intelligently create meal plans that are optimized. Fundamentally, the system uses a Multi-Criteria Decision Making (MCDM) method to assess meals based on user-specified priorities and weighted nutritional components: protein, carbs, and fat. To enable consistent scoring across different magnitudes, nutrient values are normalized using the MinMaxScaler technique. The meals are ranked using a weighted scoring model according to user preferences. The system uses a customized version of the Honey Badger Optimization (HBO) algorithm, a swarm intelligence-based meta-heuristic that mimics honey badger foraging behavior to maximize the overall nutrient satisfaction score, to determine the best meal combination. The model's ability to match meal recommendations with user nutritional goals is demonstrated by its 90% prediction and recommendation accuracy. The complete solution is provided by an interactive web application that was created with Streamlit and features an easy-to-use interface that lets users customize inputs like diet type, preferred cuisine, and nutrient importance.