Tackling issues earlier through smarter use of data
Download as PPTX, PDF0 likes219 views
The document outlines the objectives of the Essex Data Programme, which aims to improve school readiness in Basildon through predictive analytics and community engagement. It details the program's methodology, including the use of risk stratification and data-driven insights to inform interventions, and highlights key results showing the identification of at-risk children for better targeting of resources. Future steps involve co-production with local families to enhance the program's effectiveness and explore additional predictive models in other areas such as domestic abuse.
Tackling issues earlier through smarter use of data
- 2. Objectives of the session 1. To share the ambition and work of The Essex Data Programme 2. To bring to life with a working model – predicting school readiness in Basildon 3. To highlight future opportunities and learning to date 4. Q&A and group discussion
- 3. Rethinking commissioning – 8 common features 1. Engaging with citizens and communities in a profoundly different and immersive way 2. Creating (or collaborating to create) a transformative vision focused on outcomes 3. Discerning about what is simple and what is complex 4. Being comfortable with complexity and uncertainty, and helping others to be comfortable with it 5. Investing in and managing relationships across a system to reach common goals 6. Designing solutions, drawing on good data, expertise, methods and approaches 7. Making a clear and compelling case for different and better 8. Always thinking long-term
- 4. They have tried to mobilise very different types of teams
- 5. Theory of change for Co-produced solutions Risk Stratification Data Outputs Local Insight Community Assets The ambition…
- 6. The Essex Data Programme A partnership programme of work led by ECC A pilot programme with PredictX – testing, learning and building whole-system capability Using data to shift from I think to I know this is a problem Using data to improve outcomes and reduce demand and cost A programme that seeks to provide the capability and capacity to safely share and match data across Essex partners so that it can be used to provide insight and to predict risk to inform where and how to direct resources.
- 7. Essex Data is made up of…. A programme team The Predict X safe data sharing platform A series of predictive risk prototypes
- 8. Essex Data is nationally innovative…. Focus on predictive analytics, not just operational flows across a system Using whole-system data not just data from one organisation or one sector The
- 9. Predictive Analytics in a nutshell Forecasting Customer Segmentation and behavioural insights Risk Stratification Pathway modelling, Simulation & Scenario models Predictive analytics is about using data about the past to plan for current and future needs, demands and behaviours. Working with PredictX to create models and generate insight about the future
- 10. Predictive Analytics in a nutshell Predictive analytics is about using data about the past to plan for current and future needs, demands and behaviours. Creating models and generating insight about the future Risk Stratification • Creates risk scores and/or pathways • Risk = Probability that an outcome is achieved • Used for targeting resources where they are most needed • Creates risk and resilience profiles and pathways What we know about people now What might happen in the future
- 11. Can we use insight from ED to triangulate with other insight to commission differently to increase the number of children who are school ready? Can we predict which children will not be school ready on starting school in reception? Predicting communities in Basildon who are most at risk of not being school ready. School Readiness….The Ask https://www.youtube.com/watch?v=3J2S82vjb 8U&feature=youtu.be
- 12. School Readiness….what we did • Data from ECC, Basildon BC and Essex Police which is pseudonymised at source and matched at household level. • Results are displayed at output area level and will enable targeted intervention at a community level which was considered the right level for this work. • Using predictive risk models to triangulate with other insight to agree a suite of changes and or interventions that will enable ‘best start in life’. Theory of change for Co-produced solutions Risk Stratification Data Outputs Local Insight Community Assets
- 13. School Readiness…. Ethics Cabinet Office Data Science Ethical Framework – 6 Key Principles
- 14. School Readiness….The Results • In Basildon those who are known to services are 1.5 times more likely to not be ready for school • This leaves a sizeable cohort (1,539 over the four year period of the data) of school starters that are not known to services and that were ‘not school ready’. • The risk model would have correctly identified half of these at ‘risk of being not ready’ – which is 2 times better than random. • The model is 75% accurate enabling resource to be targeted to those communities that would benefit from it the most. • Financial stability & presence of anti-social behaviour are the most significant social and environmental factors.
- 15. School Readiness….The Results Highest Risk Areas
- 16. Using the Insight Combining insight sources June/July 2017 Agree co- production plan September Co-deliver changes October onwards First potentially impacted children enter school Sept 2018 School readiness data available March 2019 Next steps • Local families engaged and asked to share their views on key factors – insight collected by TONIC • TONIC insight + assets register + data profile used to inform a process of co- production with the community. • The recommendations will enable more effective shaping and focus of existing resource and capacity that will lead to more children getting the best start in life by being ready for school, improving their longer term outcomes and reducing service demand later on.
- 17. Developing future prototypes 1. Agreement of the problem to be tackled & assessment of ethics 2. Identification of data required and ISPs 3. Load data, create risk model, generate insight 4. Application of ED insight, along with other information to inform service reform activity 5. Delivery of reformed services to improve outcomes for local people, reduce cost and/or demand Informationgovernance Culturechange Finding the right problem
- 18. Future prototypes concepts Theme Domestic Abuse What are we seeking to understand? Can we predict earlier those who are likely to experience domestic abuse? To enable change Earlier intervention and preventionHealth and Social Care Can we predict earlier those who have preventable reasons for hospital admission such as first time falls?
- 19. Some key lessons so far… Need to specify the predictive problem and the relevant data sets – is a data solution right for this problem? Enabling cross partner data share is as much about the culture, politics and organisational capacity as the enabling technology Ethical consideration needs to be integral within project design and delivery – how to balance the duty to protect with the duty to prevent? Communities want to be involved in designing and delivering change.
- 20. Group discussion… How can we help communities understand the benefits of sharing and using their data? How can we measure and understand the public benefit of using data? What are the risks associated with using data and of not using data? Julia Ross Chief Strategist Care and Health PredictX julia.ross@predictx.com 07725653654 Dave Hill Executive Director, Social Care & Education Essex County Council Dave.Hill@essex.gov.uk