Christina Last


Former position

Research Data Scientist


Christina Last is a Research Data Scientist in the Research Engineering Group at the Turing, where she specialises in building machine learning solutions to understand our built environment. Her work bridges active mobility, urban data science, and machine learning operations. Christina has collaborated with a number of city governments and international organizations on software, data science, and strategic planning, in both developed and rapidly developing urban environments in the US, the UK, and Vietnam. She has led various international research projects, most recently as a Senior Data Scientist collaborating with UNICEF to model air quality during COVID-19 lockdowns using machine learning.

Before joining the Turing, Christina was the Lead Data Scientist at a property technology start up, where she managed the development of the data ecosystem and machine learning algorithms to aid the real estate investment deal flow - from sourcing and purchasing to managing residential real estate. She holds a Bachelors from the Department of Geography at the University of Bristol, and completed a sabbatical at the University of California. In her spare time Christina, devotes her time to building tech communities as the AICamp London Chapter Lead, most recently forming a partnership with Google London.

Research interests

Christina’s work at Turing will combine her interests in urban data science and natural language processing, she will work on Living With Machines, a collaboration between historians, data scientists, geographers, computational linguists, and curators at the British Library; and the Universities of Cambridge, East Anglia, Exeter, and London (QMUL); to examine the human impact of industrial revolution. She will develop toponym matching techniques using deep learning to identify and link key geographic features to textual descriptions from archival documents.

In the future, Christina is interested in modelling pedestrian flows using novel measurement and machine learning analysis techniques in developing urban environments, in order to identify communities to understand where walking and non-motorized transportation options should be prioritized. She aims to develop software and hardware solutions to lay the groundwork for permanent and long-term improvements to walking conditions on the city’s streets.