Data and code for: Uncovering commercial activity in informal cities

<p><span>Knowledge of the spatial organisation of economic activity within a city is </span><span>key to policy concerns. However, in developing cities with high levels of in</span><span>formality, this information is often unavailable. Recent progress in machine </span><span>learning together with the availability of street imagery offers an affordable</span> <span>and easily automated solution. Here we propose an algorithm that can de</span><span>tect what we call</span> <span>visible firms</span> <span>using street view imagery. Using Medellín,</span> <span>Colombia as a case study, we illustrate how this approach can be used to </span><span>uncover previously unseen economic activity.</span></p> <p><span>This dataset contains the data and code required to replicate our analysis for the manuscript: </span><span>"Uncovering commercial activity in informal cities."</span></p>