Early Prediction of Obesity Risk in Older Adults using XGBoost Classifier

Obesity is a complex disorder caused by hereditary, environmental, and behavioural factors. This work proposes a solid predictive model for assessing obesity risk, with a stunning 96% accuracy rate. The model use machine learning approaches to categorise individuals into different obesity risk categories based on pertinent variables such as demographic information, lifestyle habits, and medical history. The generated model predicts obesity risk levels with improved accuracy thanks to thorough data preparation, feature engineering, and model optimisation. With an accuracy of 96%, the model assists healthcare providers in identifying individuals with varied levels of obesity risk, allowing for focused interventions and personalised health management plans. Further research and validation efforts are needed to evaluate the model's efficacy across varied populations and healthcare contexts, assuring wider acceptance and applicability in real-world healthcare practice.