Authors:
S. Rubin Bose, J. Angelin Jeba, N. Christy Evangeline, R. Regin, P. Parmasvian, S. Sharan Jeev
Addresses:
School of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Electronics and Communication Engineering, S.A. Engineering College, Chennai, Tamil Nadu, India. Department of Electronics and Instrumentation Engineering, Madras Institute of Technology, Chennai, Tamil Nadu, India. Department of Research and Development, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India. Department of Cybersecurity, University of Texas at Dallas, Richardson, Texas, United States of America.
Abstract:
Diet prevents obesity, diabetes, hypertension, and cardiovascular disease and improves mental and physical health. Traditional diet planning often relies on generic guidelines or dietitian consultations that may not account for lifestyle, eating habits, or health issues. Universal strategies rarely work, restricting their ability to encourage good behaviour. User-specific data informs our machine learning-based Diet Recommendation System. Diet, fruit and vegetable consumption, fast food consumption, physical activity, exercise regimens, and other lifestyle factors are considered. Individualised nutritional advice is based on age, gender, height, weight, and BMI. Divide people into Balanced, Weight-Loss, High-Protein, and Low-Carbohydrate diets using Random Forests, XGBoost, and SVMs. Preprocessed structured datasets ensure consistent model training and validation, as well as precision and reliability. The technology accurately predicts and provides dependable, individualised dietary advice tailored to users' lives and interests, according to experiments. This technology leverages data-driven intelligence and nutrition science to make diet planning more successful, scalable, and accessible, especially for individuals without nutritional coaching. The study shows how machine learning may make diet planning dynamic, user-centric, and health-focused, helping people eat healthier. User comments and updated recommendations can enhance the algorithm as health and habits change. Diets work because they adapt to life.
Keywords: Diet Prediction; Machine Learning; Dietary Habits; Lifestyle Patterns; Random Forest; XGBoost and SVM Models; Support Vector Machine (SVM); Health Recommendation; Cardiovascular Disorders.
Received: 22/01/2025, Revised: 13/05/2025, Accepted: 19/07/2025, Published: 12/12/2025
DOI: 10.64091/ATICS.2025.000215
AVE Trends in Intelligent Computing Systems, 2025 Vol. 2 No. 4 , Pages: 230-240