SlideShare a Scribd company logo
1 of 18
SAS founded in 2013 in Paris | https://linkurio.us | @linkurious
Stopping money
laundering with graph
analytics.
Today’s agenda.
1. Primer on anti-money
laundering
2. AML and graph analytics, a
match made in heaven
3. Concrete examples
What is anti-money
laundering (AML)?
1. Collection of
dirty money
2. Placement
3. Layering
4. Integration
The FinCEN files
show how difficult
stopping financial
crime is.
It’s hard to connect
the dots.
The graph approach
provides a
foundation to build
a 360° view of the
clients.
Why use graph
technology in AML?
Traditional
approach
Graph
approach
Slow investigations Investigations up to 5x faster
Uncertain decisions Act with a complete picture
Analytics geared towards individual
behaviors
Focus on the complex schemes of
criminal networks
Linkurious
Enterprise, the
investigation
platform for graph
data.
Our synthetic AML
dataset.
A wide range of AML
use cases can be
tackled with graph
analytics.
Structuring. Synthetic
identities.
UBOs.
AML
investigations.
Sanctions
screening.
Entity
resolution.
Local exploration:
who this person
sent money to in
the last 30 days?
MATCH (a:BANK_ACCOUNT)
WHERE ID(a) = 10272
WITH a
MATCH p = (a)-
[:HAS_TRANSFERED|HAS_BANK_ACCOUNT*..3]-
(b:PERSON)
WITH p
WHERE ALL (rel IN relationships(p) WHERE
datetime(rel.date) < datetime() - duration({days:
30}) OR rel.date IS NULL)
RETURN p
Local exploration:
who are the
Ultimate Beneficial
Owners (UBOs) of
this company?
MATCH (a)
WHERE ID(a) = 15
WITH a
MATCH p = (a)<-[:IS_SHAREHOLDER_OF*..10]-(b)
WHERE ALL (
r IN relationships(p)
WHERE r.ownership > 0.20
)
RETURN p
Global exploration:
who received
>$10K in small cash
deposits
(structuring)?
MATCH (a:BANK_ACCOUNT)-[r:HAS_RECEIVED]-
>(b:TRANSACTION)
WHERE datetime(b.date) > datetime() -
duration({days: 90}) AND b.type = "Check"
WITH a, collect(r) as rels, sum(b.amount) as total
WHERE total>10000
RETURN a,rels,total
Global exploration:
are there money
mules (structuring)?
MATCH p = (a:TRANSACTION)-[:HOP*3..10]-
>(b:TRANSACTION)
WHERE b.amount > 0.7 * a.amount AND a.amount
> b.amount AND localtime() +
duration.between(date(a.date),date(b.date)) <
localtime() + duration({days: 90})
WITH p, nodes(p) as tx
WHERE ALL(idx in range(0, size(tx)-2) WHERE
(tx[idx]).date < (tx[idx+1]).date)
RETURN p
Global exploration:
are there people
sharing personal
information (fake
identity)?
CALL gds.graph.create.cypher(
'individual-graph',
'MATCH (n) WHERE n:PERSON RETURN id(n) AS
id',
'MATCH (a)-
[:HAS_IP_ADDRESS|HAS_EMAIL|HAS_ADDRESS|HA
S_PHONE_NUMBER]->(PI)<-
[:HAS_IP_ADDRESS|HAS_EMAIL|HAS_EMAIL|HAS_
PHONE_NUMBER]-(b) RETURN id(a) AS source,
id(b) AS target'
);
CALL gds.wcc.write('individual-graph', {
writeProperty: 'componentId' })
YIELD nodePropertiesWritten, componentCount;
How it works.
Data
preparation.
Graph
database.
Linkurious
Enterprise.
Stop criminal
networks.
Your team identifies
the relevant data
sources for your
project.
A graph expert
imports your data in
a graph database, it’s
a matter of days for
structured data.
Your analysts work
with a graph expert
to customize the look
and feel of Linkurious
Enterprise and setup
alerts and query
templates based on
your requirements.
Your analysts
connect to Linkurious
Enterprise or access
it via an existing app
to detect and
investigate criminal
networks.
Linkurious
Enterprise and
Neo4j help stop
money
laundering.
Detect new AML schemes
Go beyond the limitations of traditional
analytics to identify UBOs, structuring,
synthetic identities and more.
Accelerate investigations
With a 360° view of your clients, quickly
explore data to build a comprehensive
understanding of any situation and act
confidently.
Questions?
www.linkurio.us
contact@linkurio.us

More Related Content

More from Neo4j

More from Neo4j (20)

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
 
SWIFT: Maintaining Critical Standards in the Financial Services Industry with...
SWIFT: Maintaining Critical Standards in the Financial Services Industry with...SWIFT: Maintaining Critical Standards in the Financial Services Industry with...
SWIFT: Maintaining Critical Standards in the Financial Services Industry with...
 
Deloitte & Red Cross: Talk to your data with Knowledge-enriched Generative AI
Deloitte & Red Cross: Talk to your data with Knowledge-enriched Generative AIDeloitte & Red Cross: Talk to your data with Knowledge-enriched Generative AI
Deloitte & Red Cross: Talk to your data with Knowledge-enriched Generative AI
 
Ingka Digital: Linked Metadata by Design
Ingka Digital: Linked Metadata by DesignIngka Digital: Linked Metadata by Design
Ingka Digital: Linked Metadata by Design
 
Discover Neo4j Aura_ The Future of Graph Database-as-a-Service Workshop_3.13.24
Discover Neo4j Aura_ The Future of Graph Database-as-a-Service Workshop_3.13.24Discover Neo4j Aura_ The Future of Graph Database-as-a-Service Workshop_3.13.24
Discover Neo4j Aura_ The Future of Graph Database-as-a-Service Workshop_3.13.24
 
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptx
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptxGraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptx
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptx
 
Emil Eifrem at GraphSummit Copenhagen 2024 - The Art of the Possible.pptx
Emil Eifrem at GraphSummit Copenhagen 2024 - The Art of the Possible.pptxEmil Eifrem at GraphSummit Copenhagen 2024 - The Art of the Possible.pptx
Emil Eifrem at GraphSummit Copenhagen 2024 - The Art of the Possible.pptx
 

Recently uploaded

Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
WSO2
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
?#DUbAI#??##{{(☎️+971_581248768%)**%*]'#abortion pills for sale in dubai@
 

Recently uploaded (20)

TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with Milvus
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontology
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 

Stopping Money Laundering with Graph Analytics

  • 1. SAS founded in 2013 in Paris | https://linkurio.us | @linkurious Stopping money laundering with graph analytics.
  • 2. Today’s agenda. 1. Primer on anti-money laundering 2. AML and graph analytics, a match made in heaven 3. Concrete examples
  • 3. What is anti-money laundering (AML)? 1. Collection of dirty money 2. Placement 3. Layering 4. Integration
  • 4. The FinCEN files show how difficult stopping financial crime is.
  • 5. It’s hard to connect the dots.
  • 6. The graph approach provides a foundation to build a 360° view of the clients.
  • 7. Why use graph technology in AML? Traditional approach Graph approach Slow investigations Investigations up to 5x faster Uncertain decisions Act with a complete picture Analytics geared towards individual behaviors Focus on the complex schemes of criminal networks
  • 10. A wide range of AML use cases can be tackled with graph analytics. Structuring. Synthetic identities. UBOs. AML investigations. Sanctions screening. Entity resolution.
  • 11. Local exploration: who this person sent money to in the last 30 days? MATCH (a:BANK_ACCOUNT) WHERE ID(a) = 10272 WITH a MATCH p = (a)- [:HAS_TRANSFERED|HAS_BANK_ACCOUNT*..3]- (b:PERSON) WITH p WHERE ALL (rel IN relationships(p) WHERE datetime(rel.date) < datetime() - duration({days: 30}) OR rel.date IS NULL) RETURN p
  • 12. Local exploration: who are the Ultimate Beneficial Owners (UBOs) of this company? MATCH (a) WHERE ID(a) = 15 WITH a MATCH p = (a)<-[:IS_SHAREHOLDER_OF*..10]-(b) WHERE ALL ( r IN relationships(p) WHERE r.ownership > 0.20 ) RETURN p
  • 13. Global exploration: who received >$10K in small cash deposits (structuring)? MATCH (a:BANK_ACCOUNT)-[r:HAS_RECEIVED]- >(b:TRANSACTION) WHERE datetime(b.date) > datetime() - duration({days: 90}) AND b.type = "Check" WITH a, collect(r) as rels, sum(b.amount) as total WHERE total>10000 RETURN a,rels,total
  • 14. Global exploration: are there money mules (structuring)? MATCH p = (a:TRANSACTION)-[:HOP*3..10]- >(b:TRANSACTION) WHERE b.amount > 0.7 * a.amount AND a.amount > b.amount AND localtime() + duration.between(date(a.date),date(b.date)) < localtime() + duration({days: 90}) WITH p, nodes(p) as tx WHERE ALL(idx in range(0, size(tx)-2) WHERE (tx[idx]).date < (tx[idx+1]).date) RETURN p
  • 15. Global exploration: are there people sharing personal information (fake identity)? CALL gds.graph.create.cypher( 'individual-graph', 'MATCH (n) WHERE n:PERSON RETURN id(n) AS id', 'MATCH (a)- [:HAS_IP_ADDRESS|HAS_EMAIL|HAS_ADDRESS|HA S_PHONE_NUMBER]->(PI)<- [:HAS_IP_ADDRESS|HAS_EMAIL|HAS_EMAIL|HAS_ PHONE_NUMBER]-(b) RETURN id(a) AS source, id(b) AS target' ); CALL gds.wcc.write('individual-graph', { writeProperty: 'componentId' }) YIELD nodePropertiesWritten, componentCount;
  • 16. How it works. Data preparation. Graph database. Linkurious Enterprise. Stop criminal networks. Your team identifies the relevant data sources for your project. A graph expert imports your data in a graph database, it’s a matter of days for structured data. Your analysts work with a graph expert to customize the look and feel of Linkurious Enterprise and setup alerts and query templates based on your requirements. Your analysts connect to Linkurious Enterprise or access it via an existing app to detect and investigate criminal networks.
  • 17. Linkurious Enterprise and Neo4j help stop money laundering. Detect new AML schemes Go beyond the limitations of traditional analytics to identify UBOs, structuring, synthetic identities and more. Accelerate investigations With a 360° view of your clients, quickly explore data to build a comprehensive understanding of any situation and act confidently.

Editor's Notes

  1. Today I’m going to discuss how to use graph analytics to stop money laundering
  2. My name is Jean Villedieu and I’m a co-founder of Linkurious We provide Linkurious Enterprise, a graph based investigation platform that helps analysts make sense of complex connected data It’s used in a wide range of scenarios including cyber-security and data governance but most of our clients are fighting financial crime Today I will share some tips based on our experience working with them We’ll start by a quick primer on what is AML and why it’s important Then we’ll explore why graph analytics is great for AML The bulk of the presentation will revolve around concrete examples of using graph analytics to identify money laundering schemes
  3. First of all to understand what is AML we need to understand ML The outcome or byproduct of a lot of criminal activities is money Criminals then look to introduce this money into the financial system, it’s called placement They then use different tactics to hide the illegal origins of the funds, that’s layering Finally they tend to use the money to buy nice cars or other things. That’s integration AML consists in stopping that cycle It’s critical to remove the incentives associated with crime such as corruption, drug trafficking, human trafficking and so on
  4. A couple of days ago the ICIJ and its partners published stories about the FinCEN files throughout the world That investigation was was successfully conducted with the help of LKE and Neo4j The FinCEN files are based on suspicious activity reports filed by banks when they fear that a transaction they are processing is illegal For this investigation XXX journalists spent more than a year to analyse 0.002% of the files processed by FinCEN, the organization responsible for analysing the SARs It shows how difficult analysing financial data for AML is
  5. A lot of times the analysis comes down to understanding connections For example if I’m a bank I want to know if a client is indirectly connected across a bank account, money transfers and so on to someone who has been accused of corruption If I’m not able to follow the connections, I won’t be able to identify that my client may help the corrupt official launder money
  6. The graph approach is perfect for this sort of problem By thinking about data as a set of nodes and relationships, we can uncover hidden relationships in complex datasets With graph dbs such as Neo4j, it becomes possible for a bank to build a very holistic picture of its clients
  7. Why is that 360° view so important? With traditional approaches, AML investigations are slow or error prone. Analysts need to chase information scattered across different tools and tabs Linkurious Enterprise’s intuitive UI helps accelerate your investigations and make sure you can act with the full confidence of a complete picture, no matter how complex the situation Similarly traditional tools are focused for performance reasons on queries with limited number of connections such as how many transactions has that client done in the last 30 days With its alerts dashboard powered by graph analytics, Linkurious Enterprise also uncover schemes that traditional approaches fail to detect
  8. We have built Linkurious Enterprise to help graph experts quickly turn the power of Neo4j into business impact Linkurious Enterprise is an investigation platform compatible with Neo4j It helps investigation teams detect and investigate insights hidden in graph data I will use Linkurious Enterprise in the next demo section With Linkurious Enterprise we will easily be able to turn our AML graph queries into relevant alerts or action buttons
  9. We have built a fake dataset for today’s demo It consists in 3M nodes and 40M relationships Within our graph we have clients, companies, addresses, emails, phone numbers, bank accounts, IP addresses, ATMs and transactions You can see with this schema how things are interconnected <ul class="graph-diagram-markup" data-internal-scale="1.09" data-external-scale="1"> <li class="node" data-node-id="0" data-x="-241.3221836090088" data-y="161.61944415118242"> <span class="caption">Company</span> </li> <li class="node" data-node-id="1" data-x="474.732924858867" data-y="347.8454550996833"> <span class="caption">Address</span> </li> <li class="node" data-node-id="2" data-x="1072.3954996931445" data-y="161.61944415118242"> <span class="caption">Person</span> </li> <li class="node" data-node-id="3" data-x="474.732924858867" data-y="871.3245062682637"> <span class="caption">Bank Account</span> </li> <li class="node" data-node-id="4" data-x="1443.9212136924807" data-y="0"> <span class="caption">IP Address</span> </li> <li class="node" data-node-id="5" data-x="474.732924858867" data-y="0"> <span class="caption">Phone #</span> </li> <li class="node" data-node-id="7" data-x="474.732924858867" data-y="609.8628294008591"> <span class="caption">ATM</span> </li> <li class="node" data-node-id="8" data-x="474.732924858867" data-y="1465.3130573875221"> <span class="caption">Transaction</span> </li> <li class="node" data-node-id="9" data-x="1468.1336759514766" data-y="347.8454550996833"> <span class="caption">Email Address</span> </li> <li class="relationship" data-from="0" data-to="1"></li> <li class="relationship" data-from="2" data-to="1"></li> <li class="relationship" data-from="0" data-to="3"></li> <li class="relationship" data-from="2" data-to="3"></li> <li class="relationship" data-from="2" data-to="4"></li> <li class="relationship" data-from="0" data-to="5"></li> <li class="relationship" data-from="2" data-to="5"></li> <li class="relationship" data-from="1" data-to="7"></li> <li class="relationship" data-from="2" data-to="0"> <span class="type">IS OFFICER OF</span> </li> <li class="relationship" data-from="3" data-to="8"> <span class="type">HAS SENT</span> </li> <li class="relationship" data-from="8" data-to="3"> <span class="type">HAS RECEIVED</span> </li> <li class="relationship" data-from="2" data-to="9"></li> </ul>
  10. I have prepared a demo where I’ll show a few concrete examples of applying graph analytics to answer common AML questions We will for example identify suspicious transactions structures, fake identities or beneficiary owners of a fictitious company These are just some of the ways graph analytics can tackle the challenges of AML
  11. 7a83ee13-98a8-4bc9-8455-2dbe7bab1ea4 Let’s get started Our first query will revolve around exploring the neighbourhood of a suspicious individual We want to know who this person has received money from in the last 30 days
  12. Human Kynetics Let’s try another example To comply with regulations banks need to identify for each of the companies they have as clients who are the persons who control them It’s called the UBOs This query helps us accomplish that
  13. Now let’s switch gear So far we have been focused on queries where we know the starting point Now we’re going to ask questions about our entire graph The first of those questions is “who among my clients has received more than 10K in the last 3 months
  14. Our next query revolves around the structure of the financial transactions in our graph This time we’re going to look for situations where an amount of money is moved from one account to another by being broken down into smaller transactions between intermediary accounts This process is called smurfing and is used to obfuscate the relationship between the account sending the money and the one receiving it
  15. Our last example will rely on Neo4j’s graph data science library For this example we will look into groups of clients sharing personal information such as phone numbers, addresses, email addresses, etc At first we will create a graph projection where we’re looking at how people are interconnected via personal information Next we’ll use the Weakly Connected Components algo to identify groups within our newly created graph Finally we will inspect the larger graphs
  16. How does it work? First your team needs to identify the relevant data for your project Then a graph expert (either someone from your organization, a Solutions Engineer from Linkurious or one of our partners) imports your data into a graph database Then your analysts work with a graph expert to customize the look of Linkurious Enterprise and the analytics based on your requirements Finally your analysts can use Linkurious Enterprise to investigate criminal networks, either in standalone mode or within your existing apps
  17. I hope this presentation has helped understand how to use LKE and Neo4j in AML By combining these two solutions you can accelerate AML investigations and identify complex AML schemes that would otherwise go undetected