A machine learning-based food recommendation system with nutrition estimation

Anupama Nandeppanavar, Medha Kudari, Prasanna Bammigatti and Kaveri Vakkund

International Journal of Data Analysis Techniques and Strategies, 2024, vol. 16, issue 4, 487-507

Abstract: The human body needs energy to perform various activities, which are provided by calories. The proposed work is an efficient, user-friendly tool to assist calorie calculation. The system takes inputs such as height, weight, age, gender, and daily exercise level to estimate the recommended daily caloric intake. To achieve this, three machine learning models, K-nearest neighbours (KNN), decision tree and random forest algorithms, are employed to enhance the accuracy of predictions. Model accuracy achieved is 96.4% for KNN, 97.1% for decision tree and 96.8% using random forest algorithms. In addition to providing personalised caloric intake recommendations, the proposed system also offers diet recipes for breakfast, lunch and dinner tailored to the individuals's specific needs and preferences. Through the integration of machine learning algorithms, a user-friendly GUI, and personalised diet recommendations, the project aims to promote healthier eating habits and overall well-being for users.

Keywords: accuracy; BMI; body mass index; calorie; data processing; dietary; recipes; user interface visualisation. (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=142485 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:injdan:v:16:y:2024:i:4:p:487-507

Access Statistics for this article

More articles in International Journal of Data Analysis Techniques and Strategies from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().