Context: This research project aims to analyze valuable data gathered from wearable devices like fitness trackers and smartwatches. We are specifically interested in personal attributes like age, body mass index (BMI), and everyday activities tracked by these devices.

Objective: The main objective of this article is to know the health conditions of a person using wearable devices like smartwatches.

Material/Method: Initially, we collected data from Apple Watch and Fitbit data, which had 6400 records. We employed advanced computer algorithms (logistic regression, KNN, SVC, Random Forest) to uncover patterns hidden within the health data. By linking various health factors, we gained insights into how they impact your well-being. Our approach encompasses all aspects of your health to paint a comprehensive picture, unlike fragmented views that focus solely on isolated data points. We have created a user-friendly tool that combines collected health data and offers practical advice. Finally, our proposed model recommends personalized health advice based on the data inside it, which it analyzes properly. Among all the classifiers, SVC outperformed the others with 98.12% accuracy.

Conclusion: This article aims to enhance our health awareness through machine learning. It offers personalized insights and actionable guidance based on your health data, empowering you to make informed lifestyle choices and prioritize preventive care. Our system evaluates your health status as "healthy," "healthy but with scope for improvement," or "requiring medical attention," providing tailored recommendations for optimal health outcomes. Our experimental work shows that the SVC classifier outperforms the others, i.e., with 98.12% accuracy.