Obesity Level Estimation Software based on Decision Trees

Abstract

Obesity has become a global epidemic that has doubled since 1980, with serious consequences for health in children, teenagers and adults. Obesity is a problem has been growing steadily and that is why every day appear new studies involving children obesity, especially those looking for influence factors and how to predict emergence of the condition under these factors. In this study, authors applied the SEMMA data mining methodology, to select, explore and model the data set and then three methods were selected: Decision trees (J48), Bayesian networks (Naïve Bayes) and Logistic Regression (Simple Logistic), obtaining the best results with J48 based on the metrics: Precision, recall, TP Rate and FP Rate. Finally, a software was built to use and train the selected method, using the Weka library. The results confirmed the Decision Trees technique has the best precision rate (97.4%), improving results of previous studies with similar background.