Comparison of Machine Learning Algorithms for Obesity Prediction

Obesity has plagued the world in recent years and is a serious health issue in the modern times. There are various parameters that have led to this epidemic like lifestyle changes. We have hence conducted a study to determine how well three different machine learning algorithms can predict obesity in adults. Naive Bayes, Random Forest, and OneR are the algorithms used in this study. The different parameters we have used are Precision, F1 score, Accuracy, Recall and the Area under the operating curve (AUC) to compare them. They were used to assess how well the algorithms performed. In conclusion, when compared to the One-R and Naive Bayes algorithms, the Random Forest algorithm is the most accurate and trustworthy algorithm for predicting adult obesity. The findings of this study may aid medical practitioners in identifying people who are at risk of becoming obese and in establishing preventative strategies to lower the likelihood of obesity-related health issues.