Maximising the impact of early help resources

By Sep 24, 2018, 12:00 PM


Faced with ongoing cuts to funding, public sector agencies need to leverage advanced analytics to improves outcomes for vulnerable groups, and in doing so address the demand for interventions that are causing the greatest financial pressure.

Applying advanced analytics (AI, machine learning etc) to address this challenge requires a range of new skills and the integration of disparate technologies (new and legacy platforms) - and to deliver real change this needs to happen across partner organisations.

Critically, organisations (and partnerships) need to make sure that these technologies are being deployed in an ethical way that protects the privacy rights of the public as well as protecting the rights of vulnerable people – who are at greater risk if data is not shared.

In this context, over the past 10 years, we have worked with central and local government clients to evolve the Fusion platform. This platform has been designed to accelerate the adoption of advanced analytics and provide the controls to ensure that these technologies are being deployed in a way that addresses key ethical and Information Governance challenges.

The Fusion platform is being configured to better target early help services and reduce financial pressures in several business domains, including;

· children’s services,

· adult social care and health,

· housing / homelessness,

· community safety

In all these deployments, very careful consideration is given by data owners as to what data will be supplied and under what circumstances it can be shared.

Critically, the Fusion platform only shares data about vulnerable people if they are showing signs of distress and where there is already an agency / professional working with family. The system does not make any decisions about subsequent interventions or services; these decisions should be and are always be made by professionals / case workers.

In common with other parts of the public and private sector, public sector agencies have an opportunity to become more efficient and effective through the application of advanced analytics.

The Fusion platform helps our clients improve outcomes for vulnerable people as well as target their limited resources more effectively.

Media coverage - a welcome debate / discussion

By Wajid Shafiq Sep 19, 2018, 1:25 PM

We welcome the Guardian and Telegraph articles which represent a balanced perspective on the opportunities, challenges and risks in adopting new analytical approaches in Children’s Services. We would like to make the following observations and clarifications on the deployment of our data sharing and analytics platform:

Councils are facing a cash crisis that is pushing child services to tipping point , with “MPs warning that unless action is taken the funding crisis could cause another tragedy like the Baby P scandal”. In this context councils need to make sure that they are doing everything they can to target less resource more effectively. It is a ‘win/win’ if they can do that by providing support for families earlier, helping to prevent a problem worsening and avoiding more costly interventions later.

Although great strides have been made since the Baby P case, the wider system still needs to do more to join up data across public sector agencies so that we can better identify at-risk families and prevent tragic outcomes for children, between 2007 and 2014, nationally 260 children still died at the hand of their parents .

In common with other parts of the public and private sector, councils have an opportunity to become more efficient and effective through the application of advanced analytics. The challenge is how to use these technologies to drive data sharing that is open, proportionate and compliant with data protection legislation.

In response to these challenges, we are working with our clients to develop an approach that only shares data about families if they are showing signs of distress and where there is already an agency / professional working with family .

The system does not make any decisions about subsequent interventions or services; these decisions should be and are always be made by professionals / case workers.

We believe that the work we are undertaking is critical to improving outcomes for vulnerable people as well as enabling our clients to target its limited resources more effectively.

Public Finance Innovation Award Winners 2018

By Wajid Shafiq Sep 19, 2018, 12:52 PM

We were delighted to have been awarded the Public Finance Awards, Solutions Partner of the year 2018. The award was for the work we have been doing with London Ventures (London Councils and EY) to deliver cost savings and efficiency benefits to our children’s services clients.

Judges were impressed the ‘breadth of partnership working, the size of the estimated costs savings and efficiency benefits. It’s a good replicable project working with data to develop the service”. For more information visit https://www.publicfinanceawards.co.uk/2018-winners...

Circle overview

By Sep 11, 2018, 12:30 PM


Free to download and free to use, circle keeps you in touch with friends, relatives, parents and children, letting them know you are safe, where you are or alerting them if you need assistance.




What is circle?

Circle is a general safety app. Circle has been designed to help you stay connected by putting you one tap away from your friends and family - your very own safety network.

Circle helps you look out for the people you care about and worry a little less when they are out of sight. It is free to download and free to use and works on the one thing that we always carry around - our Smartphone.

Circle has been developed in collaboration with community safety teams from Southwark Council, Enfield Council and a number of voluntary sector organisations.

How does it work?

Circle has 4 main functions; Check in, interrupt me, come and get me and the Safe site locator.

Check-in: Let your family and friends know where you are.

How often do you find yourself receiving calls or texts just to ask 'where are you?' It can be difficult or inconvenient to reassure your family and friends all the time with phone calls and texts. Circle just sends a Check in message with one touch of a button.

Collect me: Get help when you need it

Sometimes we all find ourselves in need of some help; a lost wallet or purse or lose track of your friends on a night out. There are times when we just need to ask someone we trust to come to our assistance. Send a Collect me message to your safety network of family and friends with your location with one touch of a button.

Interrupt me: Feeling uncomfortable and need to excuse yourself?

Feeling a bit uncomfortable and need a reason to excuse yourself? Being hassled by someone in the pub but finding it difficult to make a phone call or send a text? Send a one touch Interrupt me message

Safe site locator: Find your nearest safe locations

If you find yourself away from home and feeling vulnerable and need to find a place of safety, you can tap on the 'safe site' locator and circle will present you with your nearest police stations and 'safe sites' that have been approved by your local council.

London Wide Pilot

London Councils Capital Ambition Programme are supporting a London-wide pilot of Circle with Southwark Council as the lead Borough.

Xantura’s Circle app will help Councils:

· Build knowledge of how digital technology can empower vulnerable people.

· Improve the effectiveness and take pressure off service interventions.

· Support Early Help with hidden populations.

For more information on how to capitalise on this opportunity and understand the benefits Circle can have for your service teams and your budgets, please contact us.

Alogorithm guided decision making in the public sector

By Wajid Shafiq Feb 4, 2016, 2:32 PM

Given rising pressure from demographic change and shrinking finances; the public sector is having to look for new ways to support and manage demand.

In parallel, there is an on-going explosion in sources and volumes of data available (and a reduction in the technical cost to make sense of this data) to understand and predict future demand.

Consequently, there is a growing interest in using this data (and related Big Data technologies) to build algorithms that support more timely and accurate decision making – whether this is to support strategic commissioning decisions or the targeting of interventions.

Challenges to the wider use of algorithmic approaches tend to be based on;

  • ethical considerations around whether algorithmic approaches could inadvertently embed operational bias
  • a lack of confidence that accurate algorithms can be built,
  • a related issue in terms of the impact of false positives and false negatives generated by algorithms,
  • information governance issues related to the use of multi-agency data as inputs into algorithms

Ethical challenges are often premised on the assumption that algorithms will be implemented as an autonomous system. Although there are a few examples in the private sector (ie financial credit scoring systems) it is highly unlikely that this type of autonomous implementation would occur in the public sector.

More realistically, algorithms are used to support and guide human decision making processes – which in the public sector generally occur in a well-defined policy context and where provision of services is concerned, through clear eligibility criteria. If system bias exists then it would more likely be a result of policy or eligibility bias – areas where assurances and controls (should) already exist.

With respect to the quality of input data; there is significant variation in data quality across service areas - ranging from very high quality data in Benefits, Education systems etc. to more ad-hoc data in some commissioned provider organisations. Ultimately, the real test of whether this is a show stopper lies in a comparison between algorithm supported and unsupported business processes.

However, no algorithm (or human decision making process) is free from error, the challenge lies in building business processes that minimise the harm that results from error. In our experience the complexity of these challenges varies by business area. For example the implementation of algorithms to detect fraud present significantly fewer challenges than those designed to detect children at risk of harm.

These complexities are driven by a number of factors, including (for example);

  • whether we are trying to detect historic undeclared behaviour or predict future events,
  • consent based issues,
  • ‘black box’ nature of algorithms,
  • whether resulting interventions are punitive.

In the context of the public sector, all of the above issues feed into a general sense of wariness that often emerges as an Information Governance (data sharing) challenge. Unless carefully considered, this has the ability to limit the data available for algorithm development and consequently accuracy of models.

Given the pressures faced by the public sector, using algorithms to augment human decision making is essential so that scarce resources are better managed and targeted. This is obviously more problematic where algorithms are being developed to target punitive interventions in systems with a recognised bias, for example the policing system.

From a wider perspective tech giants will continue the drive to autonomous implementation of algorithms (e.g. driverless cars) – driven by perceived public demand but in the absence of an analysis of the wider positive and negative impacts on society.

- See more at: http://www.nesta.org.uk/blog/shadow-smart-machine-...

Early Help Profiling System

By Hannah Celia Feb 4, 2016, 2:32 PM

Version 1.0 of Xantura’s Early Help Profiling System model is now built and is performing well. Four Local Authorities are moving into a controlled pilot phase and embedding the system within their front door processes. The model is identifying families who urgently need support in order to stop their risk escalating to the point of needing statutory intervention and is also triggering a review for families whose risk appears to be reducing so that they can be systematically stepped down. The modelling process has identified certain combinations of risk factors are that are critical for families and that when these issues occur, a different response should be given in order to prevent escalation.

To support a controlled deployment, Xantura have built a pre-production Insight environment. This environment can be used to validate how the outputs will be used before deployment to live. Within this, Xantura have surfaced cases that have clearly shown where the existing system has not worked for families and increased the risk of failures within Children’s Services. There has already been some critical learning about the role of partners and the joint responsibility for Early Help from looking at the historic cases in the test environment and this will continue to surface as the model evolves. It is also clear from the test cases that without the whole picture of circumstances, some families will not be picked up early enough to do preventative work.

Having the ability to understand the differences between families gives a fresh direction to the Troubled Families programme where Authorities are struggling to allocate appropriate provision to such large number of families. Social Workers are excited to have a tool that strengthens their practice and has answered their cries for a joined up view of what all agencies know about a family. Managers have welcomed the strategic analysis to support their decision making about Early Help provision and help them prioritise which families to offer support to.

Xantura Insight and risk model has strengthened the triage and assessment process and is supporting the operational implementation of a step up and step down model of support across Children’s Social Care and partnership organisations. As more and more data becomes available, Xantura will be refining the model and releasing quarterly updates.

IRRV Performance Award Winners October 2015

By Mark Dale Oct 15, 2015, 11:24 AM

Our congratulations go to both East Riding Council Benefits Team (Winners of the Benefits Team of the Year) and to the London Borough of Southwark Benefits Team (Highly Commended) at the annual IRRV conference held in Telford.

Both of the successful teams utilise the Northgate Housing Benefit processing system and the fully integrated risk based verification service provided by Xantura. The risk based verification service realises both processing efficiencies and improves fraud and error detection within the Housing Benefit and Council Tax Reduction claims process.


Children's services leaders call for big changes to Ofsted inspection system

By Wajid Shafiq Oct 9, 2015, 10:14 AM

A joint policy paper published by the Association of Directors of Children’s Services (ADCS), the Local Government Association (LGA) and council chief executive’s group Solace, recommends Ofsted’s single inspection framework is “stood down” because it is “no longer fit for purpose” as it fails to assess the involvement of other agencies and places too great a burden on departments.

They are asking for the introduction of unannounced inspections of “front-door” arrangements covering contact, referral and assessment procedures and systems.

Authorities where significant concerns were identified would be subject, along with other services working with children and young people, to a wider, multi-agency joint inspection.

They also want an expansion of thematic inspections focused on assessing performance across services for children and young people on a range of issues saying that this would become the “bedrock of improvement” and focus on issues all local areas struggle with such as tackling domestic violence.