CODALoop aims to investigate the potential of data-driven learning and behavior adaptation feedback loops for reducing energy consumption in urban communities. Big data sets are often used to describe specific urban phenomena (e.g. mobility) in aggregate ways. Less is known regarding the capacity of data analytics to represent complex individual behavior, yielding information that activates individual, community and policy learning processes aimed at reducing energy consumption. We answer two questions: Which new insights can urban big data sets provide into the impact of urban lifestyles on energy consumption? How can urban big data analytics be performed and used to enable learning and behavior adaptation at individual and community levels, and policy innovation at the urban level? We focus on two learning and adaptation/innovation feedback loops: individual-community and community-policy. Project outputs are: a) cognitive models for shared use of big data sets, b) platforms for community learning across the city, and c) policy recommendations for city governments. CODALoop integrates different disciplines and combines qualitative and quantitative research methods. The research experiments in specific urban areas through embedded living lab approaches that are jointly run by the research institutions and public and private end-users participating in the consortium.
|Effective start/end date||1/03/16 → 28/02/19|
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.