Prediction of Obesity Levels Based on Eating Habits and Physical Conditions Using Machine Learning

Predicting obesity levels based on eating habits and physical condition is a critical step in understanding important information related to obesity. In this study, a model was developed to predict obesity levels using data collected from Mexico, Peru, and Colombia. The dataset contains 2111 records and 17 features. Initially, the data were converted to categorical variables and then divided into training and test sets. The data were normalized, and models were developed using various machine learning algorithms (Decision Trees, Artificial Neural Networks, K-Nearest Neighbors, Ensemble SVM, and Naive Bayes). The performance of these models was evaluated using metrics such as accuracy, precision, recall, and F1 score. According to the results obtained, this model successfully performed with an accuracy rate of 92,89. The findings of the study indicate that obesity prediction based on eating habits and physical condition can be an important tool in health research and individual health management. Thus, more effective strategies can be developed to combat obesity.