Decision making under uncertainty is a hallmark of community planning and policy making. Formal, rigorously quantifiable means for contextualizing data and selecting useful models, assist in making these decisions more equitable, just, and economical. In this research, we explore important behavior within stochastic service networks that impact performance outcomes. We assess networks’ performance under changes to scheduling, pricing and other logistical factors. Specific examples we will discuss include overflow systems for enhancing the quality of medical care within hospitals emergency departments and dynamical pricing on toll roads. We conclude with a new take on principled model selection using a novel parallel implementation of the reversible jump Markov chain Monte Carlo (RJMCMC) method, as implemented within an open-source library: CU-MSDSp.