Informal business activity is ubiquitous around the world, but it is nearly always uncaptured by administrative data, registries, or commercial sources. For this reason, there are rarely adequate sampling frames available for survey implementers wishing to measure the activity and characteristics of the sector. This paper presents a methodology to generate a representative sample of informal businesses using an adaptive, geographically based method called Adaptive Cluster Sampling. Developed for populations that are clustered and/or rare, this method helps with efficiently sampling Primary Sampling Units-blocks-that are fully enumerated, and from which Secondary Sampling Units-businesses-can be randomly sampled to conduct interviews. The paper shows how this methodology can be applied to surveying informal businesses, often reducing both the average variance of population estimates and fieldwork effort. Practical considerations and guidance for implementation and analysis are also provided.