SlideShare a Scribd company logo
1 of 13
© 2022 Todo1 Services, Inc. All rights reserved.
Using Graphs to Take Down
Fraudsters in Real Time
Edgar Osuna, Ph.D.
Chief Data & Analytics Officer
© 2022 Todo1 Services, Inc. All rights reserved.
Agenda
• About TODO1
• Use Case: Digital Banking Fraud Detection (Real Time)
• Why is this problem hard ?
• Why Neo4j ?
• Operational Footprint
• Challenges and next steps
2
© 2022 Todo1 Services, Inc. All rights reserved.
About TODO1
• Mission to humanize the interaction between customers and their financial
institutions through our Digital Banking solution and components
• Born from DNA of leading Latam Banks and operating for 20+ years
• 500+ Employees in Latam and US
• Processing 7.5+ Billion transactions per year for 15+ million customers
• Relatively new to the Public Cloud and Machine Learning landscapes
• iuviProfiler is the component designed for Fraud Prevention and was
awarded a Graphie award in 2021 (Pioneer – AI for Fraud Detection in
Banking)
3
© 2022 Todo1 Services, Inc. All rights reserved.
4
• Banking digital channel
unauthorized interactions
executed on behalf of a
customer using valid
credentials
• Typical digital interactions
include login, password
change, personal information
update, transfers and all types
of payments, loan
applications, etc.
Digital Banking Fraud
© 2022 Todo1 Services, Inc. All rights reserved.
5
Use Case: Digital Banking Fraud Detection (Real Time)
01
02
M A C H I N E L E A R N I N G
m o d e l s a n d
a l g o r i t h m s
Analysis
SCORE RECOMMENDATION
0 - 1000 Decline –
Authenticate –
Review
Legitimate
Profile
Realtime activity
© 2022 Todo1 Services, Inc. All rights reserved.
6
Use Case: Digital Banking Fraud Detection (Real Time)
IA / ML / DL models
Feedback from
Case Management
Multi-channel data
Geolocation
Anti-trojan Analysis
Non-Monetary Transaction
Monetary Transaction
TODO1 Threat
Intelligence Network
IP information
Behavioral Profile
Mobile device
transactions
Device profile
© 2022 Todo1 Services, Inc. All rights reserved.
7
Why is this problem hard ?
• Severe class imbalance
• Lack of public / shared data
• Data quality (labeling, timeliness, and more…)
• “Auto-correlated” observations
• Changing fraud patterns overt time (concept drift)
• Feature generation can be extremely time consuming
• Real-time (< 100ms) response can be hard to manage
• Sheer volume makes it even more complex
• Down-time is not an option
PROBLEM
SOLUTION
IMPLEMENTATION
Why Neo4j..?
© 2022 Todo1 Services, Inc. All rights reserved.
8
Why Neo4j?
• Feature Generation Time
• Low Latency
• Resiliency
• High Throughput
• Feature Generation Time
• Concept Drift
Schema
Free
Index
Free
Adjacency
In Memory
Scalable
Cluster
© 2022 Todo1 Services, Inc. All rights reserved.
9
3.2+ BILLION
Protected Transactions per year
$40+ MILLION
In losses prevented
85% 15%
15+ MILLION
Registered Users
Peaks 15+ MILLION A DAY and 400+ per sec
Operational Footprint
© 2022 Todo1 Services, Inc. All rights reserved.
10
2.2+ BILLION
RELATIONSHIPS
< 100 ms
RESPONSE TIME
250+ MILLION NODES
Operational Footprint
© 2022 Todo1 Services, Inc. All rights reserved.
11
Challenges and next steps
• Improve backup and checkpoint processes
• Research further cypher optimization (planning, parameterization, etc.)
• Optimize hardware costs
• Build additional fraud prevention functionalities
• Enhance visualization capabilities
© 2022 Todo1 Services, Inc. All rights reserved.
12
Acknowledgements
1 2
Hernan Rodriguez,
Edison Ruiz and Juan
Henao for a ton of
brain, sweat and tears
David Richard & Alex
Rivilis for a smooth
sales process and a ton
of sense of humor
3 4
Susan DiFranco and
Rodrigo Haces for their post
implementation support and
infinite patience
CMS team for
continuous vigilance
and dedication to our
operation
© 2022 Todo1 Services, Inc. All rights reserved.
13
Thank you!
Contact us at
eosuna@todo1.com

More Related Content

Similar to Using Graphs to Take Down Fraudsters in Real Time

Service production from d3 pitfall viewpoint
Service production from d3 pitfall viewpointService production from d3 pitfall viewpoint
Service production from d3 pitfall viewpoint
Walter Liu
 
OpTier McKinsey Big Data Overview
OpTier McKinsey Big Data OverviewOpTier McKinsey Big Data Overview
OpTier McKinsey Big Data Overview
nickychu
 
McKinsey Big Data Overview
McKinsey Big Data OverviewMcKinsey Big Data Overview
McKinsey Big Data Overview
optier
 
Opening Keynote and Welcome
Opening Keynote and WelcomeOpening Keynote and Welcome
Opening Keynote and Welcome
Carahsoft
 
Powering Real­time Decision Engines in Finance and Healthcare using Open Sour...
Powering Real­time Decision Engines in Finance and Healthcare using Open Sour...Powering Real­time Decision Engines in Finance and Healthcare using Open Sour...
Powering Real­time Decision Engines in Finance and Healthcare using Open Sour...
Greg Makowski
 
McKinsey Big Data Overview
McKinsey Big Data OverviewMcKinsey Big Data Overview
McKinsey Big Data Overview
optier
 
Rethinking Data Availability and Governance in a Mobile World
Rethinking Data Availability and Governance in a Mobile WorldRethinking Data Availability and Governance in a Mobile World
Rethinking Data Availability and Governance in a Mobile World
Inside Analysis
 

Similar to Using Graphs to Take Down Fraudsters in Real Time (20)

Cloudy with a chance of downtime
Cloudy with a chance of downtimeCloudy with a chance of downtime
Cloudy with a chance of downtime
 
Cloud Billing: Enabling consumers for pay for what they use
Cloud Billing: Enabling consumers for pay for what they useCloud Billing: Enabling consumers for pay for what they use
Cloud Billing: Enabling consumers for pay for what they use
 
Service production from d3 pitfall viewpoint
Service production from d3 pitfall viewpointService production from d3 pitfall viewpoint
Service production from d3 pitfall viewpoint
 
TIC-TOC: VPN Is Dead; Are you Monetizing Its Replacement?
TIC-TOC: VPN Is Dead; Are you Monetizing Its Replacement?TIC-TOC: VPN Is Dead; Are you Monetizing Its Replacement?
TIC-TOC: VPN Is Dead; Are you Monetizing Its Replacement?
 
1. The Importance of Graphs in Government
1. The Importance of Graphs in Government1. The Importance of Graphs in Government
1. The Importance of Graphs in Government
 
BREACHED: Data Centric Security for SAP
BREACHED: Data Centric Security for SAPBREACHED: Data Centric Security for SAP
BREACHED: Data Centric Security for SAP
 
The computing age
The computing ageThe computing age
The computing age
 
OpTier McKinsey Big Data Overview
OpTier McKinsey Big Data OverviewOpTier McKinsey Big Data Overview
OpTier McKinsey Big Data Overview
 
McKinsey Big Data Overview
McKinsey Big Data OverviewMcKinsey Big Data Overview
McKinsey Big Data Overview
 
Opening Keynote and Welcome
Opening Keynote and WelcomeOpening Keynote and Welcome
Opening Keynote and Welcome
 
Powering Real­time Decision Engines in Finance and Healthcare using Open Sour...
Powering Real­time Decision Engines in Finance and Healthcare using Open Sour...Powering Real­time Decision Engines in Finance and Healthcare using Open Sour...
Powering Real­time Decision Engines in Finance and Healthcare using Open Sour...
 
There are 250 Database products, are you running the right one?
There are 250 Database products, are you running the right one?There are 250 Database products, are you running the right one?
There are 250 Database products, are you running the right one?
 
Exponential-e | Cloud Revolution Seminar at the Ritz, 20th November 2014
Exponential-e | Cloud Revolution Seminar at the Ritz, 20th November 2014Exponential-e | Cloud Revolution Seminar at the Ritz, 20th November 2014
Exponential-e | Cloud Revolution Seminar at the Ritz, 20th November 2014
 
Shield db data security
Shield db   data securityShield db   data security
Shield db data security
 
Shield db data security
Shield db   data securityShield db   data security
Shield db data security
 
Shield db data security
Shield db   data securityShield db   data security
Shield db data security
 
McKinsey Big Data Overview
McKinsey Big Data OverviewMcKinsey Big Data Overview
McKinsey Big Data Overview
 
Rethinking Data Availability and Governance in a Mobile World
Rethinking Data Availability and Governance in a Mobile WorldRethinking Data Availability and Governance in a Mobile World
Rethinking Data Availability and Governance in a Mobile World
 
Rethinking Data Availability and Governance in a Mobile World
Rethinking Data Availability and Governance in a Mobile WorldRethinking Data Availability and Governance in a Mobile World
Rethinking Data Availability and Governance in a Mobile World
 
Modernizing Edge IT with Riverbed SteelFusion
Modernizing Edge IT with Riverbed SteelFusionModernizing Edge IT with Riverbed SteelFusion
Modernizing Edge IT with Riverbed SteelFusion
 

More from Neo4j

More from Neo4j (20)

Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
 
QIAGEN: Biomedical Knowledge Graphs for Data Scientists and Bioinformaticians
QIAGEN: Biomedical Knowledge Graphs for Data Scientists and BioinformaticiansQIAGEN: Biomedical Knowledge Graphs for Data Scientists and Bioinformaticians
QIAGEN: Biomedical Knowledge Graphs for Data Scientists and Bioinformaticians
 
EY_Graph Database Powered Sustainability
EY_Graph Database Powered SustainabilityEY_Graph Database Powered Sustainability
EY_Graph Database Powered Sustainability
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
 
Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024
 
Connecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdfConnecting the Dots for Information Discovery.pdf
Connecting the Dots for Information Discovery.pdf
 
ISDEFE - GraphSummit Madrid - ARETA: Aviation Real-Time Emissions Token Accre...
ISDEFE - GraphSummit Madrid - ARETA: Aviation Real-Time Emissions Token Accre...ISDEFE - GraphSummit Madrid - ARETA: Aviation Real-Time Emissions Token Accre...
ISDEFE - GraphSummit Madrid - ARETA: Aviation Real-Time Emissions Token Accre...
 
BBVA - GraphSummit Madrid - Caso de éxito en BBVA: Optimizando con grafos
BBVA - GraphSummit Madrid - Caso de éxito en BBVA: Optimizando con grafosBBVA - GraphSummit Madrid - Caso de éxito en BBVA: Optimizando con grafos
BBVA - GraphSummit Madrid - Caso de éxito en BBVA: Optimizando con grafos
 
Graph Everywhere - Josep Taruella - Por qué Graph Data Science en tus modelos...
Graph Everywhere - Josep Taruella - Por qué Graph Data Science en tus modelos...Graph Everywhere - Josep Taruella - Por qué Graph Data Science en tus modelos...
Graph Everywhere - Josep Taruella - Por qué Graph Data Science en tus modelos...
 
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4jGraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
GraphSummit Madrid - Product Vision and Roadmap - Luis Salvador Neo4j
 
Neo4j_Exploring the Impact of Graph Technology on Financial Services.pdf
Neo4j_Exploring the Impact of Graph Technology on Financial Services.pdfNeo4j_Exploring the Impact of Graph Technology on Financial Services.pdf
Neo4j_Exploring the Impact of Graph Technology on Financial Services.pdf
 
Rabobank_Exploring the Impact of Graph Technology on Financial Services.pdf
Rabobank_Exploring the Impact of Graph Technology on Financial Services.pdfRabobank_Exploring the Impact of Graph Technology on Financial Services.pdf
Rabobank_Exploring the Impact of Graph Technology on Financial Services.pdf
 
Webinar - IA generativa e grafi Neo4j: RAG time!
Webinar - IA generativa e grafi Neo4j: RAG time!Webinar - IA generativa e grafi Neo4j: RAG time!
Webinar - IA generativa e grafi Neo4j: RAG time!
 
IA Generativa y Grafos de Neo4j: RAG time
IA Generativa y Grafos de Neo4j: RAG timeIA Generativa y Grafos de Neo4j: RAG time
IA Generativa y Grafos de Neo4j: RAG time
 
Neo4j: Data Engineering for RAG (retrieval augmented generation)
Neo4j: Data Engineering for RAG (retrieval augmented generation)Neo4j: Data Engineering for RAG (retrieval augmented generation)
Neo4j: Data Engineering for RAG (retrieval augmented generation)
 
Neo4j Graph Summit 2024 Workshop - EMEA - Breda_and_Munchen.pdf
Neo4j Graph Summit 2024 Workshop - EMEA - Breda_and_Munchen.pdfNeo4j Graph Summit 2024 Workshop - EMEA - Breda_and_Munchen.pdf
Neo4j Graph Summit 2024 Workshop - EMEA - Breda_and_Munchen.pdf
 
Enabling GenAI Breakthroughs with Knowledge Graphs
Enabling GenAI Breakthroughs with Knowledge GraphsEnabling GenAI Breakthroughs with Knowledge Graphs
Enabling GenAI Breakthroughs with Knowledge Graphs
 
Neo4j_Anurag Tandon_Product Vision and Roadmap.Benelux.pptx.pdf
Neo4j_Anurag Tandon_Product Vision and Roadmap.Benelux.pptx.pdfNeo4j_Anurag Tandon_Product Vision and Roadmap.Benelux.pptx.pdf
Neo4j_Anurag Tandon_Product Vision and Roadmap.Benelux.pptx.pdf
 
Neo4j Jesus Barrasa The Art of the Possible with Graph
Neo4j Jesus Barrasa The Art of the Possible with GraphNeo4j Jesus Barrasa The Art of the Possible with Graph
Neo4j Jesus Barrasa The Art of the Possible with Graph
 

Recently uploaded

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
 
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
 

Recently uploaded (20)

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
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
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
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Evaluating the top large language models.pdf
Evaluating the top large language models.pdfEvaluating the top large language models.pdf
Evaluating the top large language models.pdf
 
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
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
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
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
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
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
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
 
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...
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 

Using Graphs to Take Down Fraudsters in Real Time

  • 1. © 2022 Todo1 Services, Inc. All rights reserved. Using Graphs to Take Down Fraudsters in Real Time Edgar Osuna, Ph.D. Chief Data & Analytics Officer
  • 2. © 2022 Todo1 Services, Inc. All rights reserved. Agenda • About TODO1 • Use Case: Digital Banking Fraud Detection (Real Time) • Why is this problem hard ? • Why Neo4j ? • Operational Footprint • Challenges and next steps 2
  • 3. © 2022 Todo1 Services, Inc. All rights reserved. About TODO1 • Mission to humanize the interaction between customers and their financial institutions through our Digital Banking solution and components • Born from DNA of leading Latam Banks and operating for 20+ years • 500+ Employees in Latam and US • Processing 7.5+ Billion transactions per year for 15+ million customers • Relatively new to the Public Cloud and Machine Learning landscapes • iuviProfiler is the component designed for Fraud Prevention and was awarded a Graphie award in 2021 (Pioneer – AI for Fraud Detection in Banking) 3
  • 4. © 2022 Todo1 Services, Inc. All rights reserved. 4 • Banking digital channel unauthorized interactions executed on behalf of a customer using valid credentials • Typical digital interactions include login, password change, personal information update, transfers and all types of payments, loan applications, etc. Digital Banking Fraud
  • 5. © 2022 Todo1 Services, Inc. All rights reserved. 5 Use Case: Digital Banking Fraud Detection (Real Time) 01 02 M A C H I N E L E A R N I N G m o d e l s a n d a l g o r i t h m s Analysis SCORE RECOMMENDATION 0 - 1000 Decline – Authenticate – Review Legitimate Profile Realtime activity
  • 6. © 2022 Todo1 Services, Inc. All rights reserved. 6 Use Case: Digital Banking Fraud Detection (Real Time) IA / ML / DL models Feedback from Case Management Multi-channel data Geolocation Anti-trojan Analysis Non-Monetary Transaction Monetary Transaction TODO1 Threat Intelligence Network IP information Behavioral Profile Mobile device transactions Device profile
  • 7. © 2022 Todo1 Services, Inc. All rights reserved. 7 Why is this problem hard ? • Severe class imbalance • Lack of public / shared data • Data quality (labeling, timeliness, and more…) • “Auto-correlated” observations • Changing fraud patterns overt time (concept drift) • Feature generation can be extremely time consuming • Real-time (< 100ms) response can be hard to manage • Sheer volume makes it even more complex • Down-time is not an option PROBLEM SOLUTION IMPLEMENTATION Why Neo4j..?
  • 8. © 2022 Todo1 Services, Inc. All rights reserved. 8 Why Neo4j? • Feature Generation Time • Low Latency • Resiliency • High Throughput • Feature Generation Time • Concept Drift Schema Free Index Free Adjacency In Memory Scalable Cluster
  • 9. © 2022 Todo1 Services, Inc. All rights reserved. 9 3.2+ BILLION Protected Transactions per year $40+ MILLION In losses prevented 85% 15% 15+ MILLION Registered Users Peaks 15+ MILLION A DAY and 400+ per sec Operational Footprint
  • 10. © 2022 Todo1 Services, Inc. All rights reserved. 10 2.2+ BILLION RELATIONSHIPS < 100 ms RESPONSE TIME 250+ MILLION NODES Operational Footprint
  • 11. © 2022 Todo1 Services, Inc. All rights reserved. 11 Challenges and next steps • Improve backup and checkpoint processes • Research further cypher optimization (planning, parameterization, etc.) • Optimize hardware costs • Build additional fraud prevention functionalities • Enhance visualization capabilities
  • 12. © 2022 Todo1 Services, Inc. All rights reserved. 12 Acknowledgements 1 2 Hernan Rodriguez, Edison Ruiz and Juan Henao for a ton of brain, sweat and tears David Richard & Alex Rivilis for a smooth sales process and a ton of sense of humor 3 4 Susan DiFranco and Rodrigo Haces for their post implementation support and infinite patience CMS team for continuous vigilance and dedication to our operation
  • 13. © 2022 Todo1 Services, Inc. All rights reserved. 13 Thank you! Contact us at eosuna@todo1.com