Obesity Level Prediction using Machine Learning Techniques on Lifestyle and Health Indicators
Abstract
Obesity is a growing global health concern, associated with numerous comorbidities such as diabetes, cardiovascular diseases, and cancer. In this study, we analyze lifestyle and demographic data from the "ObesityDataSet_raw_and_data_sinthetic.csv" to build predictive models that classify individuals into various obesity categories. We apply machine learning algorithms such as Logistic Regression, Random Forest, and Support Vector Machine (SVM) to classify obesity levels. The results indicate that Random Forest outperforms other models with an accuracy of 95.3%. This study showcases the potential of data-driven approaches for early identification and prevention of obesity.
Keywords
Download Options
Introduction
Obesity has become a worldwide epidemic, affecting individuals across all age groups and socioeconomic statuses. The World Health Organization (WHO) classifies obesity as abnormal or excessive fat accumulation that poses a health risk. Numerous factors, including dietary habits, physical activity, genetics, and socioeconomic conditions, contribute to obesity.
With the advent of machine learning, predictive modeling has emerged as a powerful tool in healthcare. This paper aims to explore and compare various machine learning algorithms to predict obesity levels using demographic and lifestyle variables.
Conclusion
This study demonstrates the effectiveness of machine learning in predicting obesity levels based on lifestyle and health indicators. The Random Forest classifier, due to its ensemble nature, achieved the best performance. Future work could focus on using deep learning models or integrating real-time wearable device data for enhanced prediction capabilities.