Paper Contents
Abstract
This study suggests an AI-driven system offering personalized fitness and nutrition advice based on user-specific data like diet needs, activity levels, and health objectives. In contrast to generic wellness plans, this system employs a content-based filtering approach and machine learning algorithmsnamely the Random Forest algorithmto generate adaptive and user-specific suggestions. Employing Kaggle datasets and preprocessed with Python libraries Pandas, NumPy, and Scikit-learn, the system handles user inputs gathered through a Flask-based platform. It employs vectorization methods and cosine similarity to pair individuals with appropriate food and fitness choices. The system proves to offer the potential to generate real-time, user-specific plans that facilitate user-stated objectives, with better health outcomes achieved without needing excessive user history. This user-specific AI-driven solution is a critical advancement in digital health that allows for intelligent, scalable, and efficient lifestyle management.
Copyright
Copyright © 2025 Krushna Khandu Sonawane. This is an open access article distributed under the Creative Commons Attribution License.
