Data collection rose exponentially with the dawn of 21st Century, However the most important data to humans is the health data, which unfortunately is difficult to get approved for any and every public research, as medical history is very sensitive to be distributed. The only available public data which can be retrieved from institutions like the Centre for Disease Control (CDC), World Health Organization (WHO), National Health Interview Survey (NHIS), etc. only have population statistics for different attributes of a person.

What we propose here is a generative model which would learn to create a sequence of data for a population mimicking person's behavior and fitting this entire population, over the population statistics using Dynamic Bayesian Networks. The data would contain a population in which each person will have their exercise, injury and illness data over time. Various factors are interlinked within a time slice and between two time slices, such as the amount of exercise a person does at time t, depends on factors [Age, Health-Status, Person Type (Active, Sedentary, Obese)] at time t, and Exercise done at time t-1. Although the data generated by the learning model is not real, it is closer to it.