Liverpool City Council Harnesses Azure Ai Data Science to Protect Vulnerable Families
Liverpool needed to appoint a new Azure Data Partner to help them become data driven, more targeted and more proactive.
As they describe in this detailed case study Sentinel Partners leverages the powerful Ai and data management capabilities of Azure to meet the complex needs of Local Government.
For Liverpool City Council they helped meet the challenging requirements of implementing the ‘Supporting Families‘ program, which is focused on building the resilience of vulnerable families.
Administered by the Department for Levelling Up, Housing and Communities (DLUHC) the goal is driving system change so that every area has joined up, efficient local services which are able to identify families in need and provide the right support at the right time.
Azure Data Science
Achieving this required Sentinel to address functionality such as automated data integration and management to help identify and support vulnerable families, plan a research project based upon a huge, unified dataset and apply the latest Microsoft AI Machine Learning technologies to gain an understanding and risk measure of the degree of vulnerabilities for a person.
The platform collected and integrated data from 35 core data feeds into a fully matched and profiled, unified data set of residents and families across the city, and was able to identify how many families lived in the city and how many of those families needed immediate support, providing a new target cohort that was 193% larger than was previously known.
Data is matched and integrated from all available sources to provide up-to-date, accurate, and complete records of individuals and family units. Data sharing features of the platform facilitate collaborative and proactive working. This helps teams deliver the interventions that families need.
Master Data Management
A specific dashboard for Early Help was implemented, identifying over 4000 families in need of early intervention. This initial iteration of the Data Integration Platform was the enabler for real data driven transformation. The Supporting Families and Early Help teams could immediately target their efforts more effectively based on a single, most trusted, version of the truth.
The objective was to show how Liverpool’s unified data asset could be used to drive an early intervention strategy and support vulnerable people before they reach a point of crisis. Sentinel produced a Empowering MDM With Efficient Data Matching in the Cloud White Paper with the Liverpool teams that would be used as the basis for a business case across the council and key partners to obtain funding for a full implementation of this technology to drive proactive support services.
This uses Python and Java to implement the solution and integrate it into their Sentinel Data Platform. The solution runs in Microsoft Azure and utilises Azure Synapse Analytics, and an Azure Data Lake to read and write data files where needed.
Conclusion
Sentinel also addressed a number of related programs for Liverpool City Council, including the SAFE Taskforce and Vulnerable Pupils initiative, a research project to identify future vulnerability of Domestic Abuse and a Covid-19 Rapid Response project, to support the UKs first mass test-and-trace programme which took place across the Liverpool region in November 2020.
What is common to this suite of projects and to all Local Government programs is the need to aggregate data from multiple different agencies, spanning Policing, Healthcare, Socialcare and many others, into a singularity of information about citizens, that can then be understood not only historically, but also utilized to forecast and identify possible future events that can then empower multi-agency teams to act together collaboratively, and proactively.
Built upon and leveraging the powerful Azure AI and data management capabilities, the Sentinel Data Platform meets this need for Local Governments, creating a complete single view of data that then can be used to form groups of complete and accurate data.
