Maintaining an optimal body weight is a fundamental aspect of personal healthcare management, as it significantly influences overall well-being, disease prevention, and quality of life. However, many individuals face confusion due to contradictory information available online, lack of personalized guidance, and the limitations of generic weight charts and traditional formulas that fail to account for individual variations and complex interactions between demographic factors. This research proposes an AI-Powered Ideal Weight Prediction System Using Multivariate Regression Analysis designed to assist individuals in identifying their ideal body weight based on key anthropometric parameters including height, age, and gender. The proposed system utilizes machine learning algorithms to analyze user data collected through interactive input interfaces. Features such as height measurements (in centimeters), age demographics (18-100 years), and gender classifications (Male/Female) are used as input parameters for multivariate regression analysis. Multiple regression algorithms including Random Forest Regressor, Decision Tree Regressor, Support Vector Regression, and Linear Regression were implemented and compared to identify the optimal model for weight prediction. The system is trained and evaluated using a comprehensive synthetically generated dataset (n=2000 samples) incorporating realistic biological variations and age-based metabolic adjustments, with ideal weight values calculated using modified Devine formulas enhanced through multivariate analysis techniques. The performance of the models is assessed using standard evaluation metrics including R-squared (R²), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) . Experimental results demonstrate that the Random Forest Regressor with 100 estimators achieves superior prediction accuracy compared to other algorithms, effectively capturing complex non-linear relationships between demographic features and ideal weight that conventional univariate methods cannot represent. The multivariate regression approach enables the model to simultaneously analyze interactions between all three input parameters, resulting in more nuanced and personalized predictions.
Yadav et al. (Thu,) studied this question.