Algoritmos de clasificación para la detección de obesidad en adolescentes: Un estudio comparativo entre KNN y árboles de decisión

Abstract

Machine learning is a branch of artificial intelligence that focuses on developing statistical algorithms and models for computer systems to learn and improve their performance from data. Classification algorithms are a type of machine learning model used to predict the class or category of an object based on observed features or attributes. In obesity classification, these algorithms have been used to develop models that predict whether an individual has obesity based on data such as body mass index, age, gender, and other risk factors. This can help identify obesity early and implement more effective preventive and treatment interventions. This article compares the effectiveness of two algorithms in predicting obesity in adolescents using a dataset of 200 participants aged 15 to 19 and four variables (weight, age, height, and gender). The decision tree and k-nearest neighbor algorithms are compared, and it is concluded that both are effective in the classification of obesity in adolescents, although decision trees are a more accurate option.