Computational Models for Intelligence and Automation
Restaurant Menu Dish Recommendation using Content and/or Collaborative Filtering
Authors: Pradnya Randive, Manmath Ashture, Prasanna Kurkure, Pratik Kakade and Sahil Parupudi
Publishing Date: 28-08-2025
ISBN: 978-81-975670-1-8
Abstract
tAIsty is a restaurant menu recommendation system that uses both collaborative and contentbased filtering to suggest dishes to users. The system employs machine learning algorithms like Approximate Nearest Neighbors (ANN) and a vector database to efficiently match users with similar tastes and recommend dishes based on their past orders and preferences. By storing dish attributes such as ingredients and cuisine types, the system can also suggest dishes similar to a user’s current selection. The system also incorporates features such as allergy filtering to further personalize recommendations. In addition to this, in order to highlight the quality of ingredients, their expiry dates are notified to restaurants, and in turn, end users are recommended these dishes, thereby reducing food wastage. This recommendation system can be incorporated into digital menus of restaurants.
Keywords
Recommendation systems, Collaborative filtering, Content-based filtering, Vector databases, Food recommendation
Cite as
Pradnya Randive, Manmath Ashture, Prasanna Kurkure, Pratik Kakade and Sahil Parupudi, "Restaurant Menu Dish Recommendation using Content and/or Collaborative Filtering", In: Puneet Kumar Gupta (eds), Computational Models for Intelligence and Automation, SCRS, India, 2025, pp. 23-35. https://doi.org/10.56155/978-81-975670-1-8-3