Post-Pandemic Urban Future: Identification of the main trends of change in Latin America, through the application of the Delphi method

Abstract

The pandemic is a difficult subject to address due to its high degree of uncertainty. This condition is accentuated in Latin America, where limited information hinders any forecasting. Therefore, alternative methodologies are needed to identify the urban effects of the pandemic and its trends. This study applies the Delphi method to gather expert opinions on the influence of the global emergency, systematized in a consensus. Additionally, it employs machine learning algorithms to transform them into predictions. The sample is made up of 26 panelists from different Latin American countries, who participated in successive questionnaires until stable results were reached. The data reveal a pessimistic view of the post-pandemic, as well as a very slight consensus. Inequality is the main topic, while the factors of change are telework, e-commerce and emerging commuting habits. In summary, the research identifies the issues that are shaping the post-pandemic urban agenda. Delphi method of consensus-building to assess the expert’s opinions on the urban trends visible in this region of the world. Complementarily, the research uses predictive methods based on autonomous learning algorithms, which are cross-checked with the conclusions found in the first (interpretative) phase. The main objective is identifying trends of change in such an uncertain scenario as post-pandemic.