In the 16th to 18th centuries European colonized large parts of the world. Several scholars argue that the legacies of these processes are notable even today. While we know the outcome of these transformative changes, our knowledge about how they came about and how they affected peoples’ lives, both the settlers and the indigenous people is limited. The reason is the lack of data. The aim of this research program is to contribute to the literature on colonialism and global inequality by – for the first time ever – using big data and machine learning to analyze the establishment and growth of a settler colony – the Cape Colony. By expanding the Cape of Good Hope Panel (CGHP) and matching it to the South African Families Register (SAF) and the Slave Emancipation Records (SEF) we are able to analyze a complete settler population, the enslaved people who belonged to them and the indigenous work force covering almost 200 years (1660-1840). The program focuses on four inter-related themes that over the years has been the core in the scholarly debate: 1) inequality and long-term economic development, 2) living standards and social mobility, 3) social networks and the formation of settler elites 4) the economics of slavery and labor coercion. By being the first ever to use individual panel data to study long-term economic and social change in a colony the program will significantly contribute to the larger debates on economic and social development, institutions and colonialism.