Personalized Hydration Prediction: Leveraging Machine Learning to Model Daily Water Intake Based on Physical Activity and Environmental Factors

Abstract

Adequate hydration is essential for maintaining optimal health and performance, yet individual hydration needs vary due to factors such as physical activity, environmental conditions, and demographic characteristics. Traditional methods of hydration assessment often overlook these dynamic factors, making it difficult to provide personalized recommendations. This study aims to develop a Random Forest Regression model to predict daily water intake based on physical activity levels, weather conditions, and demographic information. The model was trained and evaluated using a dataset that included these variables, and performance was assessed using metrics such as Mean Squared Error (MSE), Mean Absolute Error (MAE), and R-squared (R²). The results showed that the Random Forest Regression model achieved an R² value of 0.8527, indicating that it explained over 85% of the variance in daily water intake. The MSE (0.1010) and MAE (0.2630) values confirmed that the model made accurate predictions. This study contributes to the field by offering a personalized approach to hydration prediction, which could be integrated into health applications and fitness tracking systems. By incorporating real-time physical activity data and environmental factors, the model provides dynamic hydration recommendations that can optimize health outcomes, particularly for high-risk groups such as athletes and the elderly. This research demonstrates the potential of Random Forest Regression for improving hydration management and advancing personalized health recommendations.