Obesity-related data derived from multiple complex systems spanning media, social, economic, food activity, health records, and infrastructure (sensors, smartphones, etc.) can assist us in understanding the relationship between obesity drivers for more efficient prevention and treatment. Reviewed literature shows a growing adaptation of the machine-learning model in recent years dealing with mechanisms and interventions in social influence, nutritional diet, eating behavior, physical activity, built environment, obesity prevalence prediction, distribution, and healthcare cost-related outcomes of obesity. Most models are designed to reflect through time and space at the individual level in a population, which indicates the need for a macro-level generalized population model. The model should consider all interconnected multi-system drivers to address obesity prevalence and intervention. This paper reviews existing computational models and datasets used to compute obesity outcomes to design a conceptual framework for establishing a macro-level generalized obesity model.