An AI tool is being developed to predict and prevent harm caused by component failures

Instead of waiting for a tenant to report a repair, the model will scan data from thousands of properties and flag the ones most likely to deteriorate, and the residents most likely to be harmed if they do.  PRISM (Predictive Risk Intelligence for Social housing Maintenance) is being developed through a collaboration between the University of Cambridge, Cambridge City Council and South Cambridgeshire District Council.  The system will combine satellite thermal imaging data, conventional property information, and “soft data” such as fuel poverty indicators, rent arrears, and tenant contact logs to prioritise action.