We are working with the University of Cambridge’s flagship mission on artificial intelligence (AI), ai@cam, to develop several projects that will benefit our communities.
The university has chosen 6 projects for its inaugural Local Government AI Accelerator. This is a programme that establishes a new model for how universities and government can work together to advance AI innovation in public services. Five projects that are being developed by us have been selected to take part in the initiative.
Funded by the Government’s Ministry of Housing, Communities and Local Government (MHCLG), the 12-month Accelerator pairs Cambridge researchers directly with local councils to develop practical, proof-of-concept AI solutions to real operational challenges, from automating housing data collection to detecting fly-tipping using cameras on bin lorries.
Here are our projects that are involved. These projects will explore how AI can support councils to improve services, better understand local issues and make more effective use of data. The objective within the next 12 months is to deliver what is described as a proof of concept, as opposed to something that is operationally active, in partnership with the University of Cambridge.
Predictive Risk Intelligence for Social Housing Maintenance (PRISM)
This project will explore how AI can be used to analyse housing and property data to identify homes that may be at higher risk of issues such as damp, heat loss or structural deterioration. The aim is to help us move towards more proactive maintenance, identifying problems earlier and prioritising support where it is most needed.
Human‑centred AI to better support vulnerable tenants
Working with Cambridge City Council, this project will help our officers identify tenants who may need support earlier. It will produce a clear engagement score and prioritised contact list, while keeping all decisions with staff. The aim is to improve tenant outcomes, reduce avoidable costs, and move services from reacting to problems to preventing them. The project will deliver easy‑to‑use dashboards, transparent and auditable scoring, and tools to track improvements over time. It will also create a model that other councils can adapt.
MAPLE: Map Automation for Planning and Local Efficiency
MAPLE will use AI to process the large number of maps submitted with planning applications each year. It will automatically identify and extract key information from map images and convert it into more usable data, with our officers checking results before use. This will significantly reduce manual work and speed up planning decisions, with a target to cut processing time by at least 75%. Built to be scalable and open source, MAPLE will help councils improve efficiency and build shared AI capability.
AI‑enabled surveys for housing planning
This project will automate much of the annual Housing Trajectory survey carried out by our Greater Cambridge Shared Planning service, which we share with Cambridge City Council. AI will help create surveys, send them out, manage reminders, and analyse responses, including free‑text answers, while planners retain full oversight. Live dashboards will show progress and results in real time, with GDPR‑compliant data handling throughout. The aim is to reduce administrative work, improve data quality, and provide a better experience for stakeholders. The approach will be open source so other councils can reuse it.
AI fly‑tipping detection
This project will use existing cameras on bin lorries to spot fly‑tipping automatically, reducing reliance on resident reports. AI will identify potential waste in video footage and record key details such as location, time, and images, which our staff will then review. The project will be developed using an agile, human‑led approach, with strong data protection safeguards including minimisation and anonymisation. The aim is to speed up reporting, improve fairness of service, and create a solution that could also be adapted for other issues, such as pothole detection.
Over the next year, ai@cam project teams will work closely with the Council to design, build and test their ideas, supported by clear technical guidance. Learning will be shared throughout the programme with councils, residents and policymakers, and the work will conclude with a final showcase highlighting key lessons and opportunities for wider use across local government.