Personalized Nutrition Recommendations for Arab Communities - Transforming Diet and Health through Machine Learning

Aug 5, 2026

Traditional nutrition approaches often lack cultural understanding, limiting adherence to healthy dietary patterns among Arab communities. Unique dietary customs and rapid lifestyle shifts have increased obesity and diet-related illnesses, including cardiovascular diseases and type 2 diabetes. This study addresses the gap by using Artificial Intelligence and Machine Learning to generate personalized dietary recommendations that combine dietary behaviors with cultural food preferences and health status. Four machine learning models (SVM, Logistic Regression, Random Forest, and Gradient Boosting) evaluate BMI, health issues, dietary limitations, and caloric intake to produce targeted plans. Model performance is assessed using accuracy, precision, and recall, with emphasis on ethical recommendations through bias mitigation, transparent algorithms, and fair access considerations. The work supports culturally appropriate AI-driven interventions and outlines future improvements through expanded data sources and user feedback.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages70

Reading Time2 h 56 min

AccessFree to download

Introduction

Background

Problem Statement

Gaps in current nutrition strategies for Arab populations

Challenges in integrating cultural preferences

Rochester Institute of Technology RIT Digital Institutional Repository Theses 5-2025 Personalized Nutrition Recommendations for Arab Communities: Transforming Diet and Health through Machine Learning Khalfan Aldoobi [kaa6297@rit.edu](kaa6297@rit.edu) Follow this and additional works at: [https://repository.rit.edu/theses](https://repository.rit.edu/theses) Recommended Citation Aldoobi, Khalfan, "Personalized Nutrition Recommendations for Arab Communities: Transforming Diet and Health through Machine Learning" (2025) . Thesis. Rochester Institute of Technology. Accessed from This Thesis is brought to you for free and open access by the RIT Libraries. For more information, please contact [repository@rit.edu](repository@rit.edu). Personalized Nutrition Recommendations for Arab Communities: Transforming Diet and Health through Machine Learning by Khalfan Aldoobi A Thesis Submitted in Partial Fulfilment of the Requirements for the Degree of Master of Science in Professional Studies: Data Analytics Department of Graduate Programs & Research Rochester Institute of Technology RIT Dubai May 2025 DEWA-Confidential Master of Science in Professional Studies: Data Analytics Graduate Thesis Approval Student Name: Khalfan Aldoobi Thesis Title: Personalized Nutrition Recommendations for Arab Com munities: Transforming Diet and Health through Machine Learning Graduate Committee Name: Dr. Sanjay Modak Date: Chair of Committee Name: Dr. Ioannis Karamitsos Date: Member of Committee i DEWA-Confidential Abstract A lack of cultural understanding in traditional nutrition approaches prevents proper adherence to healthy dietary patterns among individuals. The Arab population faces unique challenges due to cultural dietary customs and lifestyle changes that have made obesity and diet illnesses major global public health challenges. The rapid shift to high-calorie but undernourished foodsand less physical activity has resulted in alarming rate increases of obesity, cardiovascular diseases, and type 2 diabetes. The lack of cultural understanding in traditional nutrition approaches prevents proper adherence to healthy dietary patterns among individuals. This study focuses to fills the existing gap by applying Artificial Intelligence (AI) and Machine Learning (ML) methods to establish personal dietary recommendations for Arab populations. This research uses advanced AI methodologies to evaluate dietary behaviors while combining cultural food tastes and health status information into personalized dietary recommendations. The dietary recommendation process utilizes four machine learning models comprising SVM and Logistic Regression together with Random Forest and Gradient Boosting. The system creates customized dietary plans by evaluating several aspects including BMI values and health issues and dietary limitations together with caloric consumption information and cultural food choices. Furthermore, the research shows that Artificial Intelligence (AI) implements dietary interventions better than traditional approaches because it produces targeted recommendations which reflect individual culture. The evaluation of the model’s performance measured its accuracy together with precision and recall which yielded encouraging outcomes towards promoting healthier eating habits. To provide fair and ethical recommendations, the implementation requires solutions for data biases, solutions for restricted access to regional dietary data, and transparent algorithms. The study advances AI-driven personalized nutrition research through its framework that integrates AI techniques into culturally appropriate dietary interventions. Future research needs to work on extending data sources while integrating immediate feedback from users alongside advanced AI model development to improve forecasting precision. The implementation of AI-driven dietary systems has the potential to transform public health policies and improv

FAQs

Why do traditional nutrition approaches have limited impact on Arab communities?

They often lack cultural understanding, which reduces adherence to healthy dietary patterns.

What method does the thesis use to create personalized recommendations?

It applies AI and ML models that combine dietary behavior with cultural food tastes and health status information.

Which machine learning models are used in the dietary recommendation system?

The study uses four models: SVM and Logistic Regression, together with Random Forest and Gradient Boosting.

Aug 5, 2026

Upload by River Wang