Connecting the Dots: Early Insights from Customer Journey Mapping with Graphs.pptx

Neo4j
Neo4jOpen Source NOSQL Graph Database à Neo4j
Connecting the Dots: Early Insights from Customer Journey Mapping with Graphs.pptx
Click to edit Master title style
Connecting the dots: Early insights from customer journey mapping with graphs
Chris Roberts MS, Tracy Bibelnieks PhD, Erik Erickson PhD
Hennepin County
Hennepin County
An outline of our story
• Who We Are
• Our Graph Journey
• Use Case: Entity Resolution
• Use Case: Client Journey Mapping
• What’s Next
Who We Are
Hennepin County
Hennepin County
• MN’s most populous county - 34th most
populous county in the United States
• ~1.26 million residents
• Seven lines of business (LOBs):
Disparity Reduction, Health, Human Services, Law
Safety and Justice, Operations, Public
Works, Resident Services
Hennepin County
Integrated
Data &
Analytics
Enterprise
Data
Services
GIS
Integrated Data and Analytics
Focus on cross-LOB and strategic
business initiatives.
Integrate data via a carefully
governed and highly secured
integrated data system to produce
summary insights.
Human
Services
Law,
Safety, &
Justice
Disparities
Reduction
Public
Works
Resident
Services
Operations
Health
Who We Are
Our Graph Journey
DataTech
MongoDB
CAL Pilot
COVID-19
Inflection Pt
Dan McCreary
gave a talk on
graphs at
Datatech 2019;
sparked our
interest
Internal pilot
leveraging
existing
resources: gremlin
was no fun
Worked with the
Carlson Analytics
Lab and did a
pilot project on
food insecurity
Leveraged graph
to incorporate a
wide array of
indicators for
situational
awareness
Currently working
to move beyond
successful POCs
and establish
graphs as part of
our data suite
Hennepin County
Current Use Cases
Hennepin County
• Entity Resolution
o Better entity resolution enables better summary insights
o Leveraging multidimensional and inconsistent data
• County Client Journey
o Identify client cohorts – Community/Similarity detection
o Identify critical programs and services – Centrality
o Identify client pathway patterns – Pathfinding
o Analyzing churn
Hennepin County
Entity
Resolution
Key Question
How does a graph-based approach to entity
resolution compare to our combined
deterministic and probabilistic approach in a
relational database?
PII
Hennepin County
Entity
Resolution
Leverage index-free
adjacency
Instance model
Person
Person
Reference
ER
Groups
Person nodes
are entirely the
result of the
entity resolution
process
Point index allows
fast location
comparisons
Hennepin County
Entity
Resolution
Key Learnings and Next Steps
• Missing/inconsistent
data fields
• Accounts for degree of
PII easily
• At least equals result
quality of our well-
honed tabular
approach.
• Graph approach scales
more effectively.
Hennepin County
County
Client
Journey
Key Question
How can we provide insight into common
patterns of involvement that may help
streamline services and make them more
effective?
Person-
Month
Hennepin County
County
Client
Journey
Person
Instance Model
Events
Event
Categories
Capture schemas in highly flexible
way.
Current data model allows for
different grains in the journey
mapping.
Natively capture relationships that
are challenging in a relational
setting
Hennepin County
County
Client
Journey
Initial Approach
Person-
Month
Person
Events
Event
Categories
Create a bipartite projection from
Person and Program type nodes.
Hennepin County
County
Client
Journey
Initial Approach
Person
Event
Categories
Create a bipartite projection from
Person and Program type nodes.
Apply Louvain to detect
communities.
Analyze communities to determine
common characteristics.
Hennepin County
County
Client
Journey
Initial Results
Visualize the volume of interactions
people have with the county
(administrative burden)
There isn’t one typical pattern of
involvement with county services
Month
nodes
Event
nodes
Program node
Cluster node
Hennepin County
County
Client
Journey
Key Learnings and Next Steps
• Store analytical results in the
graph!
• Iterate on your data model.
• Center your business questions in
your data modeling.
Summary
Hennepin County
Benefits – County Client Graph Data Science
• Graphs enables the use of inconsistent data in entity resolution
• Leverage both the data and relationships in data
• Better entity resolution enables better summary insights
Action – Leveraging the Power of Graphs for Public Good
• Operationalize insights to improve delivery of services and client
experience
Thank you to the IDA team!
Hennepin County
Bryan Felix, Data Scientist Mansoor Kahn, Data Engineer
Kimberly Mandery, Data Scientist Mark Knutson, Data Engineer
Jonathan Watkins, Data Scientist Alex Long, Data Engineer
Michael Soto, Data Scientist Susan Lee-Rife, Data Strategist
Tamra Boyce, Data Strategist
1 sur 18

Recommandé

Ux and data par
Ux and dataUx and data
Ux and dataVera Kovaleva
186 vues99 diapositives
Lightning Talk #9: How UX and Data Storytelling Can Shape Policy by Mika Aldaba par
Lightning Talk #9: How UX and Data Storytelling Can Shape Policy by Mika AldabaLightning Talk #9: How UX and Data Storytelling Can Shape Policy by Mika Aldaba
Lightning Talk #9: How UX and Data Storytelling Can Shape Policy by Mika Aldabaux singapore
1.2M vues99 diapositives
Analytics Academy 2015 Presentation Slides par
Analytics Academy 2015 Presentation SlidesAnalytics Academy 2015 Presentation Slides
Analytics Academy 2015 Presentation SlidesHarvardComms
756 vues271 diapositives
1.8 Data and Performance Simplified (De Jong) par
1.8 Data and Performance Simplified (De Jong)1.8 Data and Performance Simplified (De Jong)
1.8 Data and Performance Simplified (De Jong)National Alliance to End Homelessness
623 vues55 diapositives
2.6 Expert Forum: Data and Performance Simplified par
2.6 Expert Forum: Data and Performance Simplified2.6 Expert Forum: Data and Performance Simplified
2.6 Expert Forum: Data and Performance SimplifiedNational Alliance to End Homelessness
501 vues61 diapositives
Stop The Fighting, Find Consensus: How To Manage Your Citizen Experience par
Stop The Fighting, Find Consensus: How To Manage Your Citizen ExperienceStop The Fighting, Find Consensus: How To Manage Your Citizen Experience
Stop The Fighting, Find Consensus: How To Manage Your Citizen ExperienceQualtrics
778 vues42 diapositives

Contenu connexe

Similaire à Connecting the Dots: Early Insights from Customer Journey Mapping with Graphs.pptx

Magma social media employment par
Magma social media employmentMagma social media employment
Magma social media employmentMarco Campana
1.2K vues41 diapositives
Datavores of Local Government par
Datavores of Local GovernmentDatavores of Local Government
Datavores of Local GovernmentNoel Hatch
623 vues15 diapositives
Take Charge of Your Data to Meet Fundraising Goals par
Take Charge of Your Data to Meet Fundraising GoalsTake Charge of Your Data to Meet Fundraising Goals
Take Charge of Your Data to Meet Fundraising Goalsfundchat
844 vues30 diapositives
No More Half Fast: Improving US Broadband Download Speed. Georgetown Universi... par
No More Half Fast: Improving US Broadband Download Speed. Georgetown Universi...No More Half Fast: Improving US Broadband Download Speed. Georgetown Universi...
No More Half Fast: Improving US Broadband Download Speed. Georgetown Universi...Brittne Kakulla, Ph.D.
4.1K vues26 diapositives
Using Data to Support Partner Coordination par
Using Data to Support Partner CoordinationUsing Data to Support Partner Coordination
Using Data to Support Partner CoordinationEnroll America
2.9K vues67 diapositives
Admin data census par
Admin data censusAdmin data census
Admin data censusOffice for National Statistics
435 vues20 diapositives

Similaire à Connecting the Dots: Early Insights from Customer Journey Mapping with Graphs.pptx(20)

Magma social media employment par Marco Campana
Magma social media employmentMagma social media employment
Magma social media employment
Marco Campana1.2K vues
Datavores of Local Government par Noel Hatch
Datavores of Local GovernmentDatavores of Local Government
Datavores of Local Government
Noel Hatch 623 vues
Take Charge of Your Data to Meet Fundraising Goals par fundchat
Take Charge of Your Data to Meet Fundraising GoalsTake Charge of Your Data to Meet Fundraising Goals
Take Charge of Your Data to Meet Fundraising Goals
fundchat844 vues
No More Half Fast: Improving US Broadband Download Speed. Georgetown Universi... par Brittne Kakulla, Ph.D.
No More Half Fast: Improving US Broadband Download Speed. Georgetown Universi...No More Half Fast: Improving US Broadband Download Speed. Georgetown Universi...
No More Half Fast: Improving US Broadband Download Speed. Georgetown Universi...
Using Data to Support Partner Coordination par Enroll America
Using Data to Support Partner CoordinationUsing Data to Support Partner Coordination
Using Data to Support Partner Coordination
Enroll America2.9K vues
Strategic use of digital information in Government - Rwanda-CMU-2014 par Rajiv Ranjan
Strategic use of digital information in Government - Rwanda-CMU-2014Strategic use of digital information in Government - Rwanda-CMU-2014
Strategic use of digital information in Government - Rwanda-CMU-2014
Rajiv Ranjan941 vues
DHCD E-Gov. System: Current and Future Changes par akmrahman
DHCD E-Gov. System: Current and Future ChangesDHCD E-Gov. System: Current and Future Changes
DHCD E-Gov. System: Current and Future Changes
akmrahman793 vues
Developing our Service Abilities IAOS Shanghai, Session 3 - october 2008 v1 par Petteri Baer
Developing our Service Abilities   IAOS Shanghai, Session 3 - october 2008 v1Developing our Service Abilities   IAOS Shanghai, Session 3 - october 2008 v1
Developing our Service Abilities IAOS Shanghai, Session 3 - october 2008 v1
Petteri Baer253 vues
London data and digital masterclass for councillors slides 14-Feb-20 par LG Inform Plus
London data and digital masterclass for councillors slides 14-Feb-20London data and digital masterclass for councillors slides 14-Feb-20
London data and digital masterclass for councillors slides 14-Feb-20
LG Inform Plus67 vues
Barnet customer segments 20160524 par Chris Guthrie
Barnet customer segments   20160524Barnet customer segments   20160524
Barnet customer segments 20160524
Chris Guthrie64 vues
Customer Segments - Barnet Council par Noel Hatch
Customer Segments - Barnet CouncilCustomer Segments - Barnet Council
Customer Segments - Barnet Council
Noel Hatch 878 vues
Denver Event - 2013 - Floodlight and Data Engine User Survey par KDMC
Denver Event - 2013 - Floodlight and Data Engine User SurveyDenver Event - 2013 - Floodlight and Data Engine User Survey
Denver Event - 2013 - Floodlight and Data Engine User Survey
KDMC618 vues
Why open data? par enotsluap
Why open data?Why open data?
Why open data?
enotsluap466 vues

Plus de Neo4j

FIMA 2023 Neo4j & FS - Entity Resolution.pptx par
FIMA 2023 Neo4j & FS - Entity Resolution.pptxFIMA 2023 Neo4j & FS - Entity Resolution.pptx
FIMA 2023 Neo4j & FS - Entity Resolution.pptxNeo4j
7 vues26 diapositives
Operations & Data Graph par
Operations & Data GraphOperations & Data Graph
Operations & Data GraphNeo4j
38 vues25 diapositives
TAGTTOO: La nova xarxa social par
TAGTTOO: La nova xarxa socialTAGTTOO: La nova xarxa social
TAGTTOO: La nova xarxa socialNeo4j
24 vues19 diapositives
El Arte de lo Possible par
El Arte de lo PossibleEl Arte de lo Possible
El Arte de lo PossibleNeo4j
40 vues35 diapositives
Neo4j y GenAI par
Neo4j y GenAI Neo4j y GenAI
Neo4j y GenAI Neo4j
47 vues41 diapositives
Roadmap y Novedades de producto par
Roadmap y Novedades de productoRoadmap y Novedades de producto
Roadmap y Novedades de productoNeo4j
52 vues33 diapositives

Plus de Neo4j(20)

FIMA 2023 Neo4j & FS - Entity Resolution.pptx par Neo4j
FIMA 2023 Neo4j & FS - Entity Resolution.pptxFIMA 2023 Neo4j & FS - Entity Resolution.pptx
FIMA 2023 Neo4j & FS - Entity Resolution.pptx
Neo4j7 vues
Operations & Data Graph par Neo4j
Operations & Data GraphOperations & Data Graph
Operations & Data Graph
Neo4j38 vues
TAGTTOO: La nova xarxa social par Neo4j
TAGTTOO: La nova xarxa socialTAGTTOO: La nova xarxa social
TAGTTOO: La nova xarxa social
Neo4j24 vues
El Arte de lo Possible par Neo4j
El Arte de lo PossibleEl Arte de lo Possible
El Arte de lo Possible
Neo4j40 vues
Neo4j y GenAI par Neo4j
Neo4j y GenAI Neo4j y GenAI
Neo4j y GenAI
Neo4j47 vues
Roadmap y Novedades de producto par Neo4j
Roadmap y Novedades de productoRoadmap y Novedades de producto
Roadmap y Novedades de producto
Neo4j52 vues
Neo4j : Graphes de Connaissance, IA et LLMs par Neo4j
Neo4j : Graphes de Connaissance, IA et LLMsNeo4j : Graphes de Connaissance, IA et LLMs
Neo4j : Graphes de Connaissance, IA et LLMs
Neo4j48 vues
Les nouveautés produit Neo4j par Neo4j
 Les nouveautés produit Neo4j Les nouveautés produit Neo4j
Les nouveautés produit Neo4j
Neo4j28 vues
Sopra Steria : Analyse intelligente des réseaux dans le domaine des télécommu... par Neo4j
Sopra Steria : Analyse intelligente des réseaux dans le domaine des télécommu...Sopra Steria : Analyse intelligente des réseaux dans le domaine des télécommu...
Sopra Steria : Analyse intelligente des réseaux dans le domaine des télécommu...
Neo4j25 vues
Generali : SPIDER, notre produit au cœur des enjeux Generali en termes de Com... par Neo4j
Generali : SPIDER, notre produit au cœur des enjeux Generali en termes de Com...Generali : SPIDER, notre produit au cœur des enjeux Generali en termes de Com...
Generali : SPIDER, notre produit au cœur des enjeux Generali en termes de Com...
Neo4j53 vues
Neo4j Generative AI workshop at GraphSummit London 14 Nov 2023.pdf par Neo4j
Neo4j Generative AI workshop at GraphSummit London 14 Nov 2023.pdfNeo4j Generative AI workshop at GraphSummit London 14 Nov 2023.pdf
Neo4j Generative AI workshop at GraphSummit London 14 Nov 2023.pdf
Neo4j58 vues
Neo4j & AWS Bedrock workshop at GraphSummit London 14 Nov 2023.pptx par Neo4j
Neo4j & AWS Bedrock workshop at GraphSummit London 14 Nov 2023.pptxNeo4j & AWS Bedrock workshop at GraphSummit London 14 Nov 2023.pptx
Neo4j & AWS Bedrock workshop at GraphSummit London 14 Nov 2023.pptx
Neo4j49 vues
Neo4j workshop at GraphSummit London 14 Nov 2023.pdf par Neo4j
Neo4j workshop at GraphSummit London 14 Nov 2023.pdfNeo4j workshop at GraphSummit London 14 Nov 2023.pdf
Neo4j workshop at GraphSummit London 14 Nov 2023.pdf
Neo4j51 vues
Neo4j Product Updates & Knowledge Graphs at GraphSummit London 14 Nov 2023.pptx par Neo4j
Neo4j Product Updates & Knowledge Graphs at GraphSummit London 14 Nov 2023.pptxNeo4j Product Updates & Knowledge Graphs at GraphSummit London 14 Nov 2023.pptx
Neo4j Product Updates & Knowledge Graphs at GraphSummit London 14 Nov 2023.pptx
Neo4j62 vues
AstraZeneca at Neo4j GraphSummit London 14Nov23.pptx par Neo4j
AstraZeneca at Neo4j GraphSummit London 14Nov23.pptxAstraZeneca at Neo4j GraphSummit London 14Nov23.pptx
AstraZeneca at Neo4j GraphSummit London 14Nov23.pptx
Neo4j41 vues
Google Cloud at GraphSummit London 14 Nov 2023.pptx par Neo4j
Google Cloud at GraphSummit London 14 Nov 2023.pptxGoogle Cloud at GraphSummit London 14 Nov 2023.pptx
Google Cloud at GraphSummit London 14 Nov 2023.pptx
Neo4j27 vues
The Art of the Possible with Graph - Sudhir Hasbe - GraphSummit London 14 Nov... par Neo4j
The Art of the Possible with Graph - Sudhir Hasbe - GraphSummit London 14 Nov...The Art of the Possible with Graph - Sudhir Hasbe - GraphSummit London 14 Nov...
The Art of the Possible with Graph - Sudhir Hasbe - GraphSummit London 14 Nov...
Neo4j77 vues
Northern Gas Networks and CKDelta at Neo4j GraphSummit London 14Nov23.pptx par Neo4j
Northern Gas Networks and CKDelta at Neo4j GraphSummit London 14Nov23.pptxNorthern Gas Networks and CKDelta at Neo4j GraphSummit London 14Nov23.pptx
Northern Gas Networks and CKDelta at Neo4j GraphSummit London 14Nov23.pptx
Neo4j46 vues
Peek into Neo4j Product Strategy and Roadmap par Neo4j
Peek into Neo4j Product Strategy and RoadmapPeek into Neo4j Product Strategy and Roadmap
Peek into Neo4j Product Strategy and Roadmap
Neo4j87 vues
Transforming Intelligence Analysis with Knowledge Graphs par Neo4j
Transforming Intelligence Analysis with Knowledge GraphsTransforming Intelligence Analysis with Knowledge Graphs
Transforming Intelligence Analysis with Knowledge Graphs
Neo4j61 vues

Dernier

Data Integrity for Banking and Financial Services par
Data Integrity for Banking and Financial ServicesData Integrity for Banking and Financial Services
Data Integrity for Banking and Financial ServicesPrecisely
25 vues26 diapositives
TouchLog: Finger Micro Gesture Recognition Using Photo-Reflective Sensors par
TouchLog: Finger Micro Gesture Recognition  Using Photo-Reflective SensorsTouchLog: Finger Micro Gesture Recognition  Using Photo-Reflective Sensors
TouchLog: Finger Micro Gesture Recognition Using Photo-Reflective Sensorssugiuralab
21 vues15 diapositives
Design Driven Network Assurance par
Design Driven Network AssuranceDesign Driven Network Assurance
Design Driven Network AssuranceNetwork Automation Forum
15 vues42 diapositives
Vertical User Stories par
Vertical User StoriesVertical User Stories
Vertical User StoriesMoisés Armani Ramírez
14 vues16 diapositives
Info Session November 2023.pdf par
Info Session November 2023.pdfInfo Session November 2023.pdf
Info Session November 2023.pdfAleksandraKoprivica4
13 vues15 diapositives
SAP Automation Using Bar Code and FIORI.pdf par
SAP Automation Using Bar Code and FIORI.pdfSAP Automation Using Bar Code and FIORI.pdf
SAP Automation Using Bar Code and FIORI.pdfVirendra Rai, PMP
23 vues38 diapositives

Dernier(20)

Data Integrity for Banking and Financial Services par Precisely
Data Integrity for Banking and Financial ServicesData Integrity for Banking and Financial Services
Data Integrity for Banking and Financial Services
Precisely25 vues
TouchLog: Finger Micro Gesture Recognition Using Photo-Reflective Sensors par sugiuralab
TouchLog: Finger Micro Gesture Recognition  Using Photo-Reflective SensorsTouchLog: Finger Micro Gesture Recognition  Using Photo-Reflective Sensors
TouchLog: Finger Micro Gesture Recognition Using Photo-Reflective Sensors
sugiuralab21 vues
Powerful Google developer tools for immediate impact! (2023-24) par wesley chun
Powerful Google developer tools for immediate impact! (2023-24)Powerful Google developer tools for immediate impact! (2023-24)
Powerful Google developer tools for immediate impact! (2023-24)
wesley chun10 vues
HTTP headers that make your website go faster - devs.gent November 2023 par Thijs Feryn
HTTP headers that make your website go faster - devs.gent November 2023HTTP headers that make your website go faster - devs.gent November 2023
HTTP headers that make your website go faster - devs.gent November 2023
Thijs Feryn22 vues
Future of AR - Facebook Presentation par ssuserb54b561
Future of AR - Facebook PresentationFuture of AR - Facebook Presentation
Future of AR - Facebook Presentation
ssuserb54b56115 vues
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLive par Network Automation Forum
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLiveAutomating a World-Class Technology Conference; Behind the Scenes of CiscoLive
Automating a World-Class Technology Conference; Behind the Scenes of CiscoLive
【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院 par IttrainingIttraining
【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院
【USB韌體設計課程】精選講義節錄-USB的列舉過程_艾鍗學院
Five Things You SHOULD Know About Postman par Postman
Five Things You SHOULD Know About PostmanFive Things You SHOULD Know About Postman
Five Things You SHOULD Know About Postman
Postman36 vues
Unit 1_Lecture 2_Physical Design of IoT.pdf par StephenTec
Unit 1_Lecture 2_Physical Design of IoT.pdfUnit 1_Lecture 2_Physical Design of IoT.pdf
Unit 1_Lecture 2_Physical Design of IoT.pdf
StephenTec12 vues
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas... par Bernd Ruecker
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...
Bernd Ruecker40 vues

Connecting the Dots: Early Insights from Customer Journey Mapping with Graphs.pptx

  • 2. Click to edit Master title style Connecting the dots: Early insights from customer journey mapping with graphs Chris Roberts MS, Tracy Bibelnieks PhD, Erik Erickson PhD Hennepin County
  • 3. Hennepin County An outline of our story • Who We Are • Our Graph Journey • Use Case: Entity Resolution • Use Case: Client Journey Mapping • What’s Next
  • 4. Who We Are Hennepin County Hennepin County • MN’s most populous county - 34th most populous county in the United States • ~1.26 million residents • Seven lines of business (LOBs): Disparity Reduction, Health, Human Services, Law Safety and Justice, Operations, Public Works, Resident Services
  • 5. Hennepin County Integrated Data & Analytics Enterprise Data Services GIS Integrated Data and Analytics Focus on cross-LOB and strategic business initiatives. Integrate data via a carefully governed and highly secured integrated data system to produce summary insights. Human Services Law, Safety, & Justice Disparities Reduction Public Works Resident Services Operations Health Who We Are
  • 6. Our Graph Journey DataTech MongoDB CAL Pilot COVID-19 Inflection Pt Dan McCreary gave a talk on graphs at Datatech 2019; sparked our interest Internal pilot leveraging existing resources: gremlin was no fun Worked with the Carlson Analytics Lab and did a pilot project on food insecurity Leveraged graph to incorporate a wide array of indicators for situational awareness Currently working to move beyond successful POCs and establish graphs as part of our data suite Hennepin County
  • 7. Current Use Cases Hennepin County • Entity Resolution o Better entity resolution enables better summary insights o Leveraging multidimensional and inconsistent data • County Client Journey o Identify client cohorts – Community/Similarity detection o Identify critical programs and services – Centrality o Identify client pathway patterns – Pathfinding o Analyzing churn
  • 8. Hennepin County Entity Resolution Key Question How does a graph-based approach to entity resolution compare to our combined deterministic and probabilistic approach in a relational database?
  • 9. PII Hennepin County Entity Resolution Leverage index-free adjacency Instance model Person Person Reference ER Groups Person nodes are entirely the result of the entity resolution process Point index allows fast location comparisons
  • 10. Hennepin County Entity Resolution Key Learnings and Next Steps • Missing/inconsistent data fields • Accounts for degree of PII easily • At least equals result quality of our well- honed tabular approach. • Graph approach scales more effectively.
  • 11. Hennepin County County Client Journey Key Question How can we provide insight into common patterns of involvement that may help streamline services and make them more effective?
  • 12. Person- Month Hennepin County County Client Journey Person Instance Model Events Event Categories Capture schemas in highly flexible way. Current data model allows for different grains in the journey mapping. Natively capture relationships that are challenging in a relational setting
  • 14. Hennepin County County Client Journey Initial Approach Person Event Categories Create a bipartite projection from Person and Program type nodes. Apply Louvain to detect communities. Analyze communities to determine common characteristics.
  • 15. Hennepin County County Client Journey Initial Results Visualize the volume of interactions people have with the county (administrative burden) There isn’t one typical pattern of involvement with county services Month nodes Event nodes Program node Cluster node
  • 16. Hennepin County County Client Journey Key Learnings and Next Steps • Store analytical results in the graph! • Iterate on your data model. • Center your business questions in your data modeling.
  • 17. Summary Hennepin County Benefits – County Client Graph Data Science • Graphs enables the use of inconsistent data in entity resolution • Leverage both the data and relationships in data • Better entity resolution enables better summary insights Action – Leveraging the Power of Graphs for Public Good • Operationalize insights to improve delivery of services and client experience
  • 18. Thank you to the IDA team! Hennepin County Bryan Felix, Data Scientist Mansoor Kahn, Data Engineer Kimberly Mandery, Data Scientist Mark Knutson, Data Engineer Jonathan Watkins, Data Scientist Alex Long, Data Engineer Michael Soto, Data Scientist Susan Lee-Rife, Data Strategist Tamra Boyce, Data Strategist