Personalized Recipe Recommendation System

View at publisher Summarise with VIRAT
Authors: Ms. Akilandeswari. T, Kuduthur Pradeep, Madineni Pradeep Naidu, Nagotula Yashwanth Naidu, Nidamanuri Manohar
Cited by: 0
References: 15

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This project presents a personalized website designed to help browse for new and unique healthy meals based on an individual's eating habits and style. Contrary to the usual recipe recommendation tools, the proposed framework employs NLP techniques, along with learning algorithms, thus studying context and providing nutrition-based and holistic recommendations. Fast retrieval is done through a baseline TF- IDF with cosine similarity, and deeper semantic meaning is acquired through BERT embeddings on the recipe's name, ingredients, and cooking steps for accuracy in recommendations. Personalized nutrition is made through applying the Harris-Benedict formula to estimate calorie needs based on User Profiles for diet-aware planning. Secure Cloud, through the backend, handles authentication and data management while the streamlined biomedical tool allows effortless searching, filtering, and nutrition tracking. The system is deployed on Streamlit and Vercel for universal real-time access. The analysis indicates that semantic embeddings significantly outperform models based on keywords. Calorie-based recommendations add real value to the users for improving and maintaining well-being. Planned future work consists of collaborative filtering, graph, and mobile app advanced for refining usability and personalization through neural networks.

Fields of Study & Subjects

Recommender Systems and Techniques Innovation in Digital Healthcare Systems Information Retrieval and Search Behavior

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
2131–2138
Publication date
21 January 2026
Language
EN