Abstract

• This study conducts an accuracy analysis of BMI prediction using regression algorithms, specifically decision tree and random forest regression. A dataset used in this paper was collected from the Kaggle data repository site. The dataset is split into training and testing sets to predict BMI, BMR and calories needed to maintain weight based on gender, age, weight, height, and activity level using decision tree and random forest regression algorithms. The performance accuracy of the proposed algorithms is evaluated using Root Mean Squared Error, Mean Absolute Error, R-squared, Mean Absolute Percentage Error and accuracy. The goal and content of this research are to study the prediction accuracy of decision tree and random forest regression machine learning algorithms in prediction. Analyzing BMI will be specifically focused on suggesting the daily calories to maintain weight to the user to get a healthy life that leads to a happy life.