The number of people who are obese and overweight presents a global challenge, and the development of effective interventions is hampered by a lack of research which takes in to account a joined up, whole systems approach to understanding the drivers of the phenomena. We need to better understand the collective characteristics and behaviours of the overweight and obese population and how these differ from those who maintain a healthy weight. Using the UK Biobank cohort of 500 000 adults, we develop an obesity classification system using k-means clustering. Variable selection from UK Biobank is informed by the Foresight whole system obesity map across key domains (Societal Influences, Individual Psychology, Individual Physiology, Individual Physical Activity, Physical Activity Environment). This paper presents the first study of UK Biobank participants to adopt this whole systems approach. Our classification identifies six groups of people, similar in respect to their exposure to known drivers of obesity: ‘Younger, active and working hard’, ‘Retirees with good lifestyle’ , ‘Stressed, sedentary and struggling’, Older with poor lifestyle’, ‘Younger, busy professionals’ and ‘Younger, fitter families’. Pen portraits are developed to describe the characteristics of these different groups. Multinomial logistic regression is used to demonstrate that the classification can effectively detect groups of individuals more likely to be overweight or obese. The group identified as ‘Younger, fitter families’ are observed to have a higher proportion of healthy weight, while three groups have increased relative risk of being overweight or obese: ‘Younger, active and working hard’, ‘Stressed, sedentary and struggling’ and ‘Older with poor lifestyles’. This work presents an innovative new approach to better understand the whole systems drivers of obesity which has the potential to produce meaningful tools for policy makers to better target interventions across the whole system to reduce overweight and obesity.