Predicting neighbourhood change using big data and machine learning: implications for theory, methods, and practice

Professor Karen Chapple

Funding period: 1 December 2019 – 1 December 2020
Type of funding: Seminar Series

Host institutions: University of California at Berkeley (USA) and University of Sydney (Australia)
Date: December 2019 (Berkeley) and July 2019 (Sydney)
Lead organiser: Prof. Karen Chapple (UC-Berkeley, USA)
Team members: Prof. Nicole Gurran and Dr. Somwrita Sarkar (Sydney School of Architecture, Design and Planning)
Contact: Prof. Karen Chapple

Abstract: Advances in data science, particularly if informed by critical urban theory, offer the potential to add to our understanding of how neighbourhood change occurs. For instance, real-time data on activity patterns, such as geotagged tweets, can help overturn traditional conceptions of residential segregation. Using machine learning techniques, we can analyse existing patterns of neighbourhood ascent and decline in order to predict gentrification. This project will convene an international group of urban researchers with deep interests in data science in a seminar series to be held at the University of California, Berkeley and the University of Sydney. The core members of this group have already been collaborating on a project working with big data to characterize neighbourhood change, particularly gentrification and displacement, in cities on four continents: Asia, Europe, North America, and South America. The seminar series in each venue will consist of day-long discussion focusing on theories and methods of researching neighbourhood change, connecting this group with data science researchers and critical urban stakeholders, followed by a day working with local stakeholders to examine research applications.