To help solve the climate crisis, municipalities are increasingly modifying their building codes and offering incentives to create greener buildings in their cities. But, city planners find it difficult to set and assess these policies, as most municipalities do not have the types of data used in urban building energy modelling (UBEM) that would allow their planners to forecast the impacts of various building policies. This thesis offers techniques for operating in this data-poor environment, presenting best practices for developing data-driven archetypes with machine learning, demonstrating inference of parameter values to improve archetypes by using surrogate modelling and genetic algorithms, and a demonstration of techniques for assessing residential retrofit impact in a data-limited environment, where data is neither detailed enough to create an in-depth single archetype study, nor broad enough to create an UBEM model. It will be shown that inference techniques have potential, but need a certain amount of detailed data to work, though far less than traditional UBEM techniques. For performing residential retrofit, it will be shown the lack of ideal detailed data does not present an overwhelming obstacle to drawing useful conclusions and that meaningful insight can be extracted despite the lack of precision. Overall, this thesis shows a data-poor environment, while challenging, is a viable environment for both research and policy modelling. / Graduate