Human activity encompasses a series of complex spatiotemporal processes that are difficult to model but represent an essential component of human exposure assessment. A significant empirical data source, like the American Time Use Survey (ATUS), can be leveraged to model human activity. However, tractable models require a better stratification of activity data to inform about different, but classifiable groups of individuals, that exhibit similar activity sequences and mobility patterns. Using machine learning algorithms, we developed an unsupervised classification and sequence generation method that is capable of generating coherent and stochastic sequences of activity from the ATUS data. This classification, when combined with any spatiotemporal exposure profile, allows the development of stochastic models of exposure patterns and records for groups of individuals exhibiting similar activity behaviors.