What drives societal complexity? This is a long-standing question for anthropologists, sociologists, and economists. Some have argued that environmental drivers are key, while others have argued that cultural practices, such as legal and political institutions, are necessary prerequisites for the development of societal complexity. Here we examine what predicts the settlement complexity of 1,000+ societies in the Ethnographic Atlas using 137 candidate variables. These predictors were classified in categories relating to ecology (climate, geography) or culture, similar to Mathew & Perreault (2015). Using a novel machine learning approach (conditional random forests), not suffering from Galton’s problem in cross-cultural research, we evaluate which variables predict settlement complexity. The models had relatively good predictive performance (all Spearman's rhos >.8 between observed and actual complexity). Two variables’ predictive ability, Agriculture and Subsistence Economy, largely exceeded that of other predictors. After accounting for those variables, ecological variables predicted settlement complexity at least as much as did cultural variables. Interestingly, institutional variables such as property rights and political institutions, which economists have argued to be key (e.g., North, 1991), had a relatively small impact. We discuss the benefits and limitations of the techniques used as well as the implications for understanding societal complexity. Latest version: https://tvpollet.github.io/HBES2018/Lecture_HBES.html#1 This message is intended solely for the addressee and may contain confidential and/or legally privileged information. Any use, disclosure or reproduction without the sender’s explicit consent is unauthorised and may be unlawful. If you have received this message in error, please notify Northumbria University immediately and permanently delete it. Any views or opinions expressed in this message are solely those of the author and do not necessarily represent those of the University. Northumbria University email is provided by Microsoft Office365 and is hosted within the EEA, although some information may be replicated globally for backup purposes. The University cannot guarantee that this message or any attachment is virus free or has not been intercepted and/or amended.