Objectives: India has experienced a rapid escalation of overweight and obesity rates, surpassing the global average. Obesity has emerged as a significant health concern with multiple contributing factors, including biological, genetic, social, environmental and behavioral influences. Among adolescents worldwide, obesity is a prevalent issue and poor dietary habits are considered to be the fundamental risk factors for many chronic diseases such as type II diabetes, cardiovascular disease, cancer and obesity. To address these complex problems, the use of Machine Learning (ML) techniques can facilitate the identification of patterns and factors of obesity by analyzing extensive nutritional epidemiology databases. The main aim of this study is to perform multi-class classification of obesity of adolescent girls using an ensemble of ML classifiers. Methods: A primary dataset of 2000 adolescent girls, gathered from schools and colleges in Chennai, India are input for this study. Our study investigates the obesity using ML classifier algorithms by employing 75% of the dataset for training and the remaining for testing. We have applied eleven well-known algorithms to compare and evaluate their prediction accuracies using the training and testing datasets. To assess the performance of the classifiers, the metrics such as precision, recall /sensitivity and F1-Score have been calculated and analyzed for predicting the actual outcomes. Findings: Based on our computer experimental results, the CatBoost algorithm has achieved the highest accuracy of 90.6%, when we compare with that of other classifiers. Novelty: The uniqueness of our study is collecting and analysing the primary dataset which is focused on adolescent girls, age ranging from 16 to19 and classifying the dataset using various ML algorithms. But, the most of the other studies are not focusing on this specific age group for predicting the obesity. By understanding the factors contributing to obesity in adolescent girls, the researchers can study the long-term health impacts and help the society to prepare better for future healthcare challenges.