Hybrid Recipe Recommendation System Using KNN and Collaborative Filtering Techniques

Discovering the perfect recipe or ingredient combination can be a challenge given the vast array of culinary options. Our Recipe Recommendation System addresses this by combining K-Nearest Neighbors (KNN) and collaborative filtering to offer highly personalized and accurate recipe suggestions. Using a rich dataset of recipes, ingredients, and user reviews, the system identifies similar dishes based on ingredient profiles and user preferences. KNN leverages TF-IDF vectorization and cosine similarity to find related recipes, while collaborative filtering uses Non-Negative Matrix Factorization (NMF) to analyze user behaviour and suggest personalized options. Experimental results show that the system effectively delivers diverse and relevant recommendations, enhancing the user's culinary journey.