Obesity is a prevalent global health issue, with multifaceted causes, including genetic, environmental, and lifestyle factors. One significant aspect contributing to obesity is eating habits, making it crucial to understand the relationship between dietary choices and obesity levels. This research explores the application of machine learning (ML) techniques to predict obesity levels based on eating habits. Here, a comprehensive dataset encompassing diverse demographic information, dietary patterns, and obesity levels of individuals is considered. Various machine learning algorithms, including Decision Trees, Support Vector Machines, Random Forests, and Neural Networks, are employed to develop predictive models. Feature selection methods are employed to identify the most influential dietary factors affecting obesity. The proposed approach assesses the model’s performance using metrics such as accuracy, precision, recall, and F1-score. Additionally, ML models demonstrate promising predictive capabilities, with certain algorithms outperforming others in accuracy and reliability. Moreover, feature importance analysis identifies specific food groups and consumption patterns strongly associated with obesity, providing valuable insights for targeted interventions and personalized dietary recommendations. This research contributes to the growing field of predictive healthcare analytics, offering a data-driven approach to address obesity-related challenges. The outcomes have implications for public health policies, nutrition education programs, and personalized healthcare initiatives, aiming to mitigate the obesity epidemic and promote healthier lifestyles.