SlideShare a Scribd company logo
1 of 28
We’re a charity that
builds data science
capacity in social
change organisations
We volunteer data scientists
and
Using machine learning to identify food bank dependence early
MEETS
Applying data science talent,
tools and processes to achieve
social good
Providing packs of food,
essentials and support to people
in crisis in Huddersfield and the
surrounding area
Both teams consisted of volunteers. All technical work completed ‘out of hours’
Project Funding, a real enabler
organisation
Food bank use is on the rise...
.
.
Data from the Welcome Centre
The way they are being used is also changing...
.
Data from the Welcome Centre
Food bank users are coming back more regularly and becoming dependent on the support
● Most clients visit relatively
few times
● But the few clients who visit
regularly consume a high
proportion of resources and
are at risk of becoming
dependent
● Hence need for support
Typical Journey
Client is referred
by phone
Volunteer puts
details in the
system
A food parcel is
prepared
Parcel is
collected by
client
Supported Journey
Client is referred
by phone
Volunteer puts
details in the
system
A food parcel is
prepared
Parcel is
collected by
client
Open-ended, flexible support,
100% client focused (e.g. form
completion, advocacy, grants,
listening, signposting …)
Using Machine Learning to Triage
Client is referred
by phone
Volunteer puts
details in the
system
A food parcel is
prepared
Parcel is collected by
client
Model used to
predict future
usage
High scores
referred to
support worker
The Challenge
Build a production grade
model that predicts future
visits
Integrate it into a system
written in BASIC on Windows
servers
Provide a way to retrain the
model
Have it run with zero
maintenance and
low cost
Make sure the staff
understand it
Ensure it’s GDPR
compliant
Avoid any socio-
demographic bias
The Model
** we will not be using free text fields as these are very sensitive to the agent inputting the data
Model
Client Features:
These are features that
describe the client, They are
typically static throughout a
client history.
● Address Length
● Dependent Details
● Living with Partner
● Client Issues
Current Referral Features:
These are features that
describe the current referral
● Agency
● Referral Issues
● Referral Benefit
● Referral Domestic
Circumstances
Previous Referral Features:
Features from previous
referrals
● Previous Agencies
● Previous Issues
● Previous Benefits
● Previous Domestic
Circumstances
Referral History Features:
Features derived from the
pattern of previous referrals.
● # of prev. referrals
● # of referrals in given
window lengths
● Time since last referral
Score
Extra Trees Regressor
Advanced technology
/score
/retrain
/model-status
/change-model
API Gateway
- Models
- Training data
- Training logs
- Model history
Async Retrain
...at a low and sustainable cost
AWS server
£1.20 a month!(and no local support overhead for The Welcome Centre)
Support and the model is reducing dependency
- 40 referrals per day, around 50% from new clients.
- ~10 model-based support recommendations made per day,
depending upon overall demand and the specific clients being
referred
- Very few false positives
How well is the model working? (Anecdotal)
Anecdotal evidence
- The support worker ‘trusts’ the recommendations and no longer spends
time on manual checking
- After 9 months the system is an integral part of TWC’s business
processes (not sitting on a shelf gathering dust)
Direct impacts of the Welcome Centre
Time Saving
The support worker has more time to spend in
direct contact with clients and spends less time
reviewing new client referrals
Early intervention
Allows the Welcome Centre to realise
the goal of meeting with clients at
the beginning of their journey
New Ways of Working
Facilitates the move from a purely
reactive to a more proactive way of
engaging with clients
More effective client engagement
Provision of food packs becomes part of support
management plan rather than being based on ad
hoc referrals
Wider impacts of the Welcome Centre
Enhanced strategy
Enabled more effective
proactive approach of support
service to become a ‘core’
function within TWC
Early intervention is vital
Funding bid
Funding bid for expanding the
support service submitted. This will
provide a second support worker,
backed by volunteers. Use of the
recommendations made by the
model is central to this bid
(model threshold can be adjusted to
match support capacity)
Data-driven organisation
Good data and data analysis is
now regarded as a key tool for
informing strategic decision
making at board level
Wider community impacts
Impact Aloud 2018 - Presentation
“Really inspiring and eye-opening about
what could be achieved by a small
organisation with this sort of help.”
Finalist for Best Use of Data to
Achieve Social Impact
Wider community impacts - further projects
2-year initiative to help
small charities in
London to improve their
digital skills and analysis
of data
About
DataKind UK
What does DataKind UK do?
Data Therapy
What does DataKind UK do?
Data Therapy
Data Dives
What does DataKind UK do?
Data Therapy
Data Dives
Data Corps
What does DataKind UK do?
Data Therapy
Data Dives
Data Corps
Social Data Society
What does DataKind UK do?
Data Therapy
Data Dives
Data Corps
Social Data Society
Responsible data
Giselle@DataKind.org.uk
www.datakind.org.uk
@datakinduk
Questions?

More Related Content

Similar to Using machine learning to identify food bank dependency early - Giselle Cory & Lucy Rimmington (DataKind)

Workshop 1 presentation
Workshop 1 presentationWorkshop 1 presentation
Workshop 1 presentation
net_gain
 
ICT Service Desk as a Business Partner 2015 - itSMF V
ICT Service Desk as a Business Partner 2015 - itSMF VICT Service Desk as a Business Partner 2015 - itSMF V
ICT Service Desk as a Business Partner 2015 - itSMF V
Paul Lahey
 
Multichannel Retention Strategies: A Steady Diet of Low Hanging Fruit
Multichannel Retention Strategies: A Steady Diet of Low Hanging FruitMultichannel Retention Strategies: A Steady Diet of Low Hanging Fruit
Multichannel Retention Strategies: A Steady Diet of Low Hanging Fruit
Vivastream
 
idealspace Berkeley Final Presentation
idealspace Berkeley Final Presentationidealspace Berkeley Final Presentation
idealspace Berkeley Final Presentation
Stanford University
 
Forecasting Digital Innovation
Forecasting Digital InnovationForecasting Digital Innovation
Forecasting Digital Innovation
Stefano Manca
 

Similar to Using machine learning to identify food bank dependency early - Giselle Cory & Lucy Rimmington (DataKind) (20)

customer oriented service delivery in service sector
customer oriented service delivery in service sectorcustomer oriented service delivery in service sector
customer oriented service delivery in service sector
 
Commissioners and Business Intelligence
Commissioners and Business IntelligenceCommissioners and Business Intelligence
Commissioners and Business Intelligence
 
Workshop 1 presentation
Workshop 1 presentationWorkshop 1 presentation
Workshop 1 presentation
 
Omnichannel Banking
Omnichannel BankingOmnichannel Banking
Omnichannel Banking
 
Gain Customer Insights with Data
Gain Customer Insights with DataGain Customer Insights with Data
Gain Customer Insights with Data
 
ICT Service Desk as a Business Partner 2015 - itSMF V
ICT Service Desk as a Business Partner 2015 - itSMF VICT Service Desk as a Business Partner 2015 - itSMF V
ICT Service Desk as a Business Partner 2015 - itSMF V
 
Summer Shorts: Using Predictive Analytics For Data-Driven Decisions
Summer Shorts: Using Predictive Analytics For Data-Driven DecisionsSummer Shorts: Using Predictive Analytics For Data-Driven Decisions
Summer Shorts: Using Predictive Analytics For Data-Driven Decisions
 
Grow Your Sustainer Revenue
Grow Your Sustainer RevenueGrow Your Sustainer Revenue
Grow Your Sustainer Revenue
 
Multichannel Retention Strategies: A Steady Diet of Low Hanging Fruit
Multichannel Retention Strategies: A Steady Diet of Low Hanging FruitMultichannel Retention Strategies: A Steady Diet of Low Hanging Fruit
Multichannel Retention Strategies: A Steady Diet of Low Hanging Fruit
 
Model program presentation
Model program presentationModel program presentation
Model program presentation
 
idealspace Berkeley Final Presentation
idealspace Berkeley Final Presentationidealspace Berkeley Final Presentation
idealspace Berkeley Final Presentation
 
TATA AIG GENERAL INSURANCE COMPANY LIMITED - Insurer Innovation Award 2024
TATA AIG GENERAL INSURANCE COMPANY LIMITED - Insurer Innovation Award 2024TATA AIG GENERAL INSURANCE COMPANY LIMITED - Insurer Innovation Award 2024
TATA AIG GENERAL INSURANCE COMPANY LIMITED - Insurer Innovation Award 2024
 
Atish Bakshi XIMB
Atish Bakshi XIMB Atish Bakshi XIMB
Atish Bakshi XIMB
 
Grantwriting 101
Grantwriting 101Grantwriting 101
Grantwriting 101
 
Library Hospitality: Public Relations Work, CRM Applied
Library Hospitality: Public Relations Work, CRM AppliedLibrary Hospitality: Public Relations Work, CRM Applied
Library Hospitality: Public Relations Work, CRM Applied
 
2nd shift customer care evening solutions presentation powerpoint
2nd shift customer care evening solutions presentation powerpoint2nd shift customer care evening solutions presentation powerpoint
2nd shift customer care evening solutions presentation powerpoint
 
Evolving Business Models in Digital Health
Evolving Business Models in Digital HealthEvolving Business Models in Digital Health
Evolving Business Models in Digital Health
 
Customer Insight Event 18Mar10 Lesley Courcouf
Customer Insight Event 18Mar10 Lesley Courcouf Customer Insight Event 18Mar10 Lesley Courcouf
Customer Insight Event 18Mar10 Lesley Courcouf
 
Why is Data Science still not a mainstream in corporations - Sasa Radovanovic
Why is Data Science still not a mainstream in corporations - Sasa RadovanovicWhy is Data Science still not a mainstream in corporations - Sasa Radovanovic
Why is Data Science still not a mainstream in corporations - Sasa Radovanovic
 
Forecasting Digital Innovation
Forecasting Digital InnovationForecasting Digital Innovation
Forecasting Digital Innovation
 

More from mysociety

More from mysociety (20)

Regulating Access to Information - Alex Parsons, mySociety (UK)
Regulating Access to Information - Alex Parsons, mySociety (UK)Regulating Access to Information - Alex Parsons, mySociety (UK)
Regulating Access to Information - Alex Parsons, mySociety (UK)
 
Watch this space (and pay for it): Alaveteli-driven exposure of the misuse of...
Watch this space (and pay for it): Alaveteli-driven exposure of the misuse of...Watch this space (and pay for it): Alaveteli-driven exposure of the misuse of...
Watch this space (and pay for it): Alaveteli-driven exposure of the misuse of...
 
What are the effects of OpenStreetMapping on the mappers themselves? - Aishwo...
What are the effects of OpenStreetMapping on the mappers themselves? - Aishwo...What are the effects of OpenStreetMapping on the mappers themselves? - Aishwo...
What are the effects of OpenStreetMapping on the mappers themselves? - Aishwo...
 
#PlanTech and the geospatial ecosystem - Ben Fowkes (Delib)
#PlanTech and the geospatial ecosystem - Ben Fowkes (Delib)#PlanTech and the geospatial ecosystem - Ben Fowkes (Delib)
#PlanTech and the geospatial ecosystem - Ben Fowkes (Delib)
 
Open data for local self governance: learnings from five Ukrainian cities - N...
Open data for local self governance: learnings from five Ukrainian cities - N...Open data for local self governance: learnings from five Ukrainian cities - N...
Open data for local self governance: learnings from five Ukrainian cities - N...
 
Digital Champions: community led development monitoring in Tanzania - Janet C...
Digital Champions: community led development monitoring in Tanzania - Janet C...Digital Champions: community led development monitoring in Tanzania - Janet C...
Digital Champions: community led development monitoring in Tanzania - Janet C...
 
Don’t build it: a practical guide for those building Civic Tech - Luke Jordan...
Don’t build it: a practical guide for those building Civic Tech - Luke Jordan...Don’t build it: a practical guide for those building Civic Tech - Luke Jordan...
Don’t build it: a practical guide for those building Civic Tech - Luke Jordan...
 
It takes two: when citizens and Congress Members deliberate online - Samantha...
It takes two: when citizens and Congress Members deliberate online - Samantha...It takes two: when citizens and Congress Members deliberate online - Samantha...
It takes two: when citizens and Congress Members deliberate online - Samantha...
 
Understanding the small hurdles that block community engagement, with behavio...
Understanding the small hurdles that block community engagement, with behavio...Understanding the small hurdles that block community engagement, with behavio...
Understanding the small hurdles that block community engagement, with behavio...
 
Our COVID consultation journey: from a small initiative to the desk of the pr...
Our COVID consultation journey: from a small initiative to the desk of the pr...Our COVID consultation journey: from a small initiative to the desk of the pr...
Our COVID consultation journey: from a small initiative to the desk of the pr...
 
Keeping track of open data in times of political change - David Zamora (Open ...
Keeping track of open data in times of political change - David Zamora (Open ...Keeping track of open data in times of political change - David Zamora (Open ...
Keeping track of open data in times of political change - David Zamora (Open ...
 
Civic tech vs. illicit pharmacies - Ibraheem Saleem (Code for Pakistan)
Civic tech vs. illicit pharmacies - Ibraheem Saleem (Code for Pakistan)Civic tech vs. illicit pharmacies - Ibraheem Saleem (Code for Pakistan)
Civic tech vs. illicit pharmacies - Ibraheem Saleem (Code for Pakistan)
 
Find that Charity: a tool to help find charities and improve charity data - D...
Find that Charity: a tool to help find charities and improve charity data - D...Find that Charity: a tool to help find charities and improve charity data - D...
Find that Charity: a tool to help find charities and improve charity data - D...
 
Civic tech for smartphone beginners: is the future binary? - Arran Leonard (I...
Civic tech for smartphone beginners: is the future binary? - Arran Leonard (I...Civic tech for smartphone beginners: is the future binary? - Arran Leonard (I...
Civic tech for smartphone beginners: is the future binary? - Arran Leonard (I...
 
How to monitor emergency procurement with open data: lessons from 12 countrie...
How to monitor emergency procurement with open data: lessons from 12 countrie...How to monitor emergency procurement with open data: lessons from 12 countrie...
How to monitor emergency procurement with open data: lessons from 12 countrie...
 
Accountability through petitions: Elections 2019 - Gaston Wright & Leandro As...
Accountability through petitions: Elections 2019 - Gaston Wright & Leandro As...Accountability through petitions: Elections 2019 - Gaston Wright & Leandro As...
Accountability through petitions: Elections 2019 - Gaston Wright & Leandro As...
 
Openly available air quality data: not just blue-sky thinking - Sruti Modekur...
Openly available air quality data: not just blue-sky thinking - Sruti Modekur...Openly available air quality data: not just blue-sky thinking - Sruti Modekur...
Openly available air quality data: not just blue-sky thinking - Sruti Modekur...
 
How to last in civic tech (especially now) - Matthew Stempeck & Micah L. Sifr...
How to last in civic tech (especially now) - Matthew Stempeck & Micah L. Sifr...How to last in civic tech (especially now) - Matthew Stempeck & Micah L. Sifr...
How to last in civic tech (especially now) - Matthew Stempeck & Micah L. Sifr...
 
Future of tech and democracy at the city of Reykjavík - Sigurlaug Anna Jóhann...
Future of tech and democracy at the city of Reykjavík - Sigurlaug Anna Jóhann...Future of tech and democracy at the city of Reykjavík - Sigurlaug Anna Jóhann...
Future of tech and democracy at the city of Reykjavík - Sigurlaug Anna Jóhann...
 
Lessons learned from building democracy’s database - Stacy Henderson (Cicero,...
Lessons learned from building democracy’s database - Stacy Henderson (Cicero,...Lessons learned from building democracy’s database - Stacy Henderson (Cicero,...
Lessons learned from building democracy’s database - Stacy Henderson (Cicero,...
 

Recently uploaded

Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
vu2urc
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
giselly40
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
Earley Information Science
 

Recently uploaded (20)

Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdf
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 

Using machine learning to identify food bank dependency early - Giselle Cory & Lucy Rimmington (DataKind)

  • 1.
  • 2. We’re a charity that builds data science capacity in social change organisations
  • 3.
  • 4. We volunteer data scientists
  • 5. and Using machine learning to identify food bank dependence early
  • 6. MEETS Applying data science talent, tools and processes to achieve social good Providing packs of food, essentials and support to people in crisis in Huddersfield and the surrounding area Both teams consisted of volunteers. All technical work completed ‘out of hours’ Project Funding, a real enabler organisation
  • 7. Food bank use is on the rise... . . Data from the Welcome Centre
  • 8. The way they are being used is also changing... . Data from the Welcome Centre Food bank users are coming back more regularly and becoming dependent on the support ● Most clients visit relatively few times ● But the few clients who visit regularly consume a high proportion of resources and are at risk of becoming dependent ● Hence need for support
  • 9. Typical Journey Client is referred by phone Volunteer puts details in the system A food parcel is prepared Parcel is collected by client
  • 10. Supported Journey Client is referred by phone Volunteer puts details in the system A food parcel is prepared Parcel is collected by client Open-ended, flexible support, 100% client focused (e.g. form completion, advocacy, grants, listening, signposting …)
  • 11. Using Machine Learning to Triage Client is referred by phone Volunteer puts details in the system A food parcel is prepared Parcel is collected by client Model used to predict future usage High scores referred to support worker
  • 12. The Challenge Build a production grade model that predicts future visits Integrate it into a system written in BASIC on Windows servers Provide a way to retrain the model Have it run with zero maintenance and low cost Make sure the staff understand it Ensure it’s GDPR compliant Avoid any socio- demographic bias
  • 13. The Model ** we will not be using free text fields as these are very sensitive to the agent inputting the data Model Client Features: These are features that describe the client, They are typically static throughout a client history. ● Address Length ● Dependent Details ● Living with Partner ● Client Issues Current Referral Features: These are features that describe the current referral ● Agency ● Referral Issues ● Referral Benefit ● Referral Domestic Circumstances Previous Referral Features: Features from previous referrals ● Previous Agencies ● Previous Issues ● Previous Benefits ● Previous Domestic Circumstances Referral History Features: Features derived from the pattern of previous referrals. ● # of prev. referrals ● # of referrals in given window lengths ● Time since last referral Score Extra Trees Regressor
  • 14. Advanced technology /score /retrain /model-status /change-model API Gateway - Models - Training data - Training logs - Model history Async Retrain
  • 15. ...at a low and sustainable cost AWS server £1.20 a month!(and no local support overhead for The Welcome Centre)
  • 16. Support and the model is reducing dependency
  • 17. - 40 referrals per day, around 50% from new clients. - ~10 model-based support recommendations made per day, depending upon overall demand and the specific clients being referred - Very few false positives How well is the model working? (Anecdotal) Anecdotal evidence - The support worker ‘trusts’ the recommendations and no longer spends time on manual checking - After 9 months the system is an integral part of TWC’s business processes (not sitting on a shelf gathering dust)
  • 18. Direct impacts of the Welcome Centre Time Saving The support worker has more time to spend in direct contact with clients and spends less time reviewing new client referrals Early intervention Allows the Welcome Centre to realise the goal of meeting with clients at the beginning of their journey New Ways of Working Facilitates the move from a purely reactive to a more proactive way of engaging with clients More effective client engagement Provision of food packs becomes part of support management plan rather than being based on ad hoc referrals
  • 19. Wider impacts of the Welcome Centre Enhanced strategy Enabled more effective proactive approach of support service to become a ‘core’ function within TWC Early intervention is vital Funding bid Funding bid for expanding the support service submitted. This will provide a second support worker, backed by volunteers. Use of the recommendations made by the model is central to this bid (model threshold can be adjusted to match support capacity) Data-driven organisation Good data and data analysis is now regarded as a key tool for informing strategic decision making at board level
  • 20. Wider community impacts Impact Aloud 2018 - Presentation “Really inspiring and eye-opening about what could be achieved by a small organisation with this sort of help.” Finalist for Best Use of Data to Achieve Social Impact
  • 21. Wider community impacts - further projects 2-year initiative to help small charities in London to improve their digital skills and analysis of data
  • 23. What does DataKind UK do? Data Therapy
  • 24. What does DataKind UK do? Data Therapy Data Dives
  • 25. What does DataKind UK do? Data Therapy Data Dives Data Corps
  • 26. What does DataKind UK do? Data Therapy Data Dives Data Corps Social Data Society
  • 27. What does DataKind UK do? Data Therapy Data Dives Data Corps Social Data Society Responsible data