Machine Learning Approaches For Obesity Level Classification

Abstract

Obesity has emerged as a global epidemic, posing significant public health challenges and increasing the risk of numerous chronic diseases. Accurate and timely classification of obesity levels is crucial for effective prevention, diagnosis, and personalized intervention strategies. Traditional methods, primarily relying on Body Mass Index (BMI), often fall short in capturing the complex physiological and lifestyle factors contributing to obesity. This paper explores the application of various Machine Learning (ML) approaches for the classification of obesity levels. We discuss diverse data sources, prominent ML algorithms, feature engineering techniques, and evaluation metrics pertinent to this domain. Furthermore, we highlight key challenges such as data imbalance, interpretability, and ethical considerations, alongside future directions for advancing ML in obesity management.