Keynote Presentation at GraphTalk Oslo 2023

© 2023 Neo4j, Inc. All rights reserved.
Graphs Are Everywhere!
Håkan Löfqvist, Kristof Neys
Field Engineering

Neo4j, Inc. All rights reserved 2022
“Graphs are the main modality
of data we receive from
nature…”

3

4
At the heart of every enterprise challenge
is an explosion of data complexity

5
Organizations are drowning in data
but lacking in insights

6
Data silos
hide valuable
context
THE CHALLENGE

7
CONNECTION COMPLEXITY
How do you navigate this data
explosion at scale?

8
Legacy
systems
can’t keep up
“Relational” Databases
don’t handle relationships well
Document Databases
don’t handle relationships at all

INDEX-FREE ADJACENCY: FAST, FLEXIBLE, SCALABLE
9
Relational Database
Person Person-Friend Friend
Native Graph Database
At write time
Data remains
.connected.
as it is stored
At read time
.Lightning-fast. retrieval of data and
relationships via pointer chasing

QUERY PERFORMANCE AS # OF JOINS INCREASE
10
Connectedness and Size of Data Set
Response
Time
Relational and
other NoSQL
databases
Native Graph Database
1000x Advantage
Minutes to milliseconds
5+ hops
3+ degrees
Thousands of connections
0 to 2 hops
0 to 3 degrees
Few connections

11
“we found [graph technology] to be literally
thousands of times faster than our prior MySQL
solution, with queries that require 10-100 times less
code. Graph provides eBay with functionality that
was previously impossible.” Volker Pacher - eBay

12
Neo4j enables organizations to quickly and easily
uncover hidden relationships and patterns
across billions of data connections
Powering applications that are
impossible with other technologies

13
is an explosion of data complexity

14
{
"item": 67045,
"action": "VIEWED",
"visitor": 158090,
"timestamp": 1433222276276
}
Events
{
"item": 67045,
"action": "BOUGHT",
"visitor": 158090,
"transactionid": 11220,
"timestamp": 1433193915008
}
“Real world”

15
{
"item": 67045,
"action": "VIEWED",
"visitor": 158090,
"timestamp": 1433222276276
}
Events
{
"item": 67045,
"action": "BOUGHT",
"visitor": 158090,
"transactionid": 11220,
"timestamp": 1433193915008
}
visitor action item ts tx
1 1 4231 1433222276276 null
1 3 4231 1433193915008 3223
Events Table

16
id vis_fk act_fk item_fk ts tx_fk
1 1 1 4231 1433222276276 9
2 1 3 4231 1433193915008 5
Events Table
id action
1 VIEWED
2 ADDED
Actions
id visitor
1 158090
2 273216
Visitors
id …
4231
Items
id …
9
Transaction Items

17
How do we make more money?
(We should be data driven)

18
😳

19
Still does not look anything like the real world, but best case we have some statistics about our sales

20
is a gap between the real world and data
that models it

21
Maybe Sven and Mica should
buy the Clear case too?

22
Neo4j enables organizations to quickly and easily
uncover hidden relationships and patterns
across billions of data connections
We are the Graph Technology company that helps organizations find
hidden relationships and patterns across billions of data connections
deeply, easily and quickly. Our platform offers an integrated Graph
database, Graph Data Science and a visualization engine for your
connected data.
Powering applications that are
impossible with other technologies

Graph Transactions,
Storage & Querying
Graph Analytics, ML,
& Data Science
Intelligent Applications Better Predictions
23
NEO4J: FOR APPLICATIONS AND ANALYTICS

24
20 / 20
Top US banks
3 / 5
Top Aircraft Manufacturers
7 / 10
Top Telcos
3 / 5
Top Hotel Groups
8 / 10
Top Insurance Companies
10 /10
Top Automakers
7 / 10
Top Retailers
5 / 5
Top Pharmaceuticals
Trusted by
75 of the

25
The ﬁrst-ever graph database
Creator of the market category
Continued market leader
300
1B+ Enterprise
customers
$500M
in funding
170+
Global partner
ecosystem
250K
Community of developers
and data pros
100M+
Downloads
170+
Global partner
ecosystem
250K
Community of developers
and data pros

FLEXIBLE CLOUD DEPLOYMENT MODELS
26
Graph-as-a-Service Cloud Managed Services Self-hosted
Fully-managed SaaS
Consumption-based pricing
Cloud-native
Self-service deployment
No access to underlying
infrastructure and systems
White-glove managed service
by Neo4j experts
Fully customizable deployment
model and service levels
Operate In own data centers
or Virtual Private Cloud
For private and hybrid
cloud, or on-prem
Bring your own license
Full control of your environment
Run in any cloud, in your account

27
Exponential Growth in Connected Data
Connected data
use-cases are
exploding in numbers
and in depth
Data models the real
world. Therefore data is
becoming increasingly
connected.
The world is
becoming
increasingly
connected

ICIJ Pulitzer Price Winner 2017
“Neo4j is a revolutionary discovery
tool that’s transformed our
investigative journalism process. The
Panama Papers simply wouldn’t have
been possible before on this scale. It’s
magic!”
Mar Cabra
Head of Research & Data
ICIJ

30
● Neo4j enables organizations to unlock the business value of
connections, inﬂuences and relationships in data
If it works for NASA….
David Meza, Chief Knowledge Architect at
NASA: "This has saved us at least
a year and over $2 million in
research and development
toward our Mission to Mars
planning."

Graph technology is fueling discovery and
transformation in every field
Decision
Analysis
Customer
Experience
Data
Unification
Personalization Discovery
Fraud Prevention
Network Analysis
Forecasting
Patient/Customer Journey
Behavior Prediction
Data Disambiguation
Operations Optimization
Customers/Data 360
Compliance
Product Recommendations
Media and Advertising
Personalized Health
Drug Discovery
Product/Process Innovation
Intelligence & Security
31

32
Think Knowledge Graphs!

What are Knowledge Graphs?
● Entities can be real-world objects and abstract concepts
● Relationships represent the connections between entities
● Semantic description of the entities and relationships
A knowledge graph is a structured representation of
facts, consisting of entities, relationships and semantic
descriptions

34
From Data points to a Knowledge Graph
Car
DRIVES
name: “Dan”
born: May 29, 1978
twitter: “@dan”
name: “Ann”
born: Dec 5, 1979
brand: “Volvo”
model: “V90”
description:
since:
Jan 10, 2021
LOVES
LOVES
LIVES_WITH
O
W
N
S
Person Person

User
:VISITED
Website
User
IPLocation
Website
IPLocation
Website
Website
Website
:VISITED
:VISITED
:VISITED
:USED
:USED
:
U
S
E
D
:
V
I
S
I
T
E
D
:
V
I
S
I
T
E
D
:VISITED
:SAME_AS
Graphs allow you to make implicit
relationships….
….explicit
And they grow too…?!

:SAME_AS
User
:VISITED
Website
User
IPLocation
Website
IPLocation
Website
Website
Website
:VISITED
:VISITED
:VISITED
:USED
:USED
:
U
S
E
D
:
V
I
S
I
T
E
D
:
V
I
S
I
T
E
D
:VISITED
User
:SAM
E_AS
:USED
:VISITED
PersonId: 1
PersonId: 1 PersonId: 1
User
PersonId: 2
:VISITED
…and can then group similar nodes…and
create a new graph from the explicit
relationships…
A graph grows organically - gaining
insights and enriching your data
Graphs Grow….!

37
Knowledge graphs in Credit risk analysis

38
How can you Learn from your Data?

39
From implicit to explicit…
Query your Knowledge
Graph
Graph Algorithms
Graph Native
Machine Learning
Find the patterns you’re
looking for in connected data
Use unsupervised machine
learning techniques to
identify associations,
anomalies, and trends.
Use embeddings to learn the
features in your graph that
you don’t even know are
important yet.
Train in-graph supervised ML
models to predict links,
labels, and missing data.

40
65+ Graph Algorithms - Out of the Box
Pathfinding & Search Centrality Community Detection
❏ Delta-Stepping Single-Source
❏ Dijkstra’s Single-Source
❏ Dijkstra Source-Target
❏ All Pairs Shortest Path
❏ A* Shortest Path
❏ Yen’s K Shortest Path
❏ Minimum Weight Spanning Tree
❏ Random Walk
❏ Breadth & Depth First Search
❏ Degree Centrality
❏ Closeness Centrality
❏ Harmonic Centrality
❏ Betweenness Centrality & Approx.
❏ PageRank
❏ Personalized PageRank
❏ ArticleRank
❏ Eigenvector Centrality
❏ Hyperlink Induced Topic Search (HITS)
❏ Inﬂuence Maximization (Greedy, CELF)
❏ Weakly Connected Components
❏ Strongly Connected Components
❏ Label Propagation
❏ Leiden
❏ Louvain
❏ K-Means Clustering
❏ K-1 Coloring
❏ Modularity Optimization
❏ Speaker Listener Label Propagation
❏ Approximate Max K-Cut
❏ Triangle Count
❏ Local Clustering Coefﬁcient
❏ Conductance Metric
Heuristic LP Similarity Graph Embeddings
❏ Adamic Adar
❏ Common Neighbors
❏ Preferential Attachment
❏ Resource Allocations
❏ Same Community
❏ Total Neighbors
❏ K-Nearest Neighbors (KNN)
❏ Filtered K-Nearest Neighbors (KNN)
❏ Node Similarity
❏ Filtered Node Similarity
❏ Similarity Functions
❏ Fast Random Projection (FastRP)
❏ Node2Vec
❏ GraphSAGE
❏ HashGNN

41
Before we go any further…let’s
quiz!

42
Which of the colored nodes would be considered the most
‘important'?

43
Which of the colored nodes would be considered the most
‘important'?

Graph Embeddings:
The bridge to traditional ML
44

Node Embedding
What are node embeddings?
How?
The representation of nodes as low-dimensional vectors that
summarize their graph position, the structure of their local graph
neighborhood as well as any possible node features
Encoder - Decoder Framework

Node Embedding

47
OK - we have vectors…
Now what?
Graph Machine Learning

Native Graph Machine Learning Pipelines
Node classification:
Classify entities based on their attributes & relationships
Link prediction:
Predict missing relationships or hidden links
Features: Pre-existing
attributes, algorithm
results, embeddings
Property Regression:
Predict facts about entities based on their attributes &
relationships
48

49
One last thing….
It’s better with GPT…!

50
Setting the context - From a user point of view

Leveraging LLM’s to augment Knowledge and insights
Accelerate better explainable outcomes with your data and Generative AI through Data
Augmented Generation powered by Neo4j Knowledge Graphs
Apps
Structured
Data
Unstructured
Data
Intranet
Internet
Social Media
Other online
contents
Knowledge
Extraction
Knowledge
Compression
Open Domain
Knowledge
Graph
Closed Domain
Knowledge
Graph
Knowledge
Lake
Knowledge
Enrichment
Augmented
Generation
Knowledge
Discovery
Experimentation
& Discovery
Education &
Enablement
Regulatory
Compliance
Sustainability Business Insights
Cyber
Observability
And More!
Automation
Layer
Knowledge
Layer
Data Augmented
Generation Layer
Outcomes

LEVERAGING LLMs TO DEPLOY FRONT-END APPS

53
Architecture
NeoDash
Dashboard UI
Neo4j
Free text input
APOC call Graph representations
Embeddings
Graph visualization of results
NeoDash
Dashboard UI
Persist results
Conceptual flow for a
text-to-graph or graph-to-text
application based on Neo4j +
OpenAI.

54
Some examples…

55

56

57

58
How Data Pro’s are using Graphs…

59
https://www.orbitmi.com/blog/how-neo4j-enables-orbit-ai-routing

60
Customer Case Study:
Logistics and Supply Chain
Plan maritime routes based on distances,
costs, and internal logic.
Results:
● Subsecond maritime routes planning
● Reduce global carbon emissions
60,000 tons
● 12-16M ROI for OrbitMI customers
“We wanted to create a solution that exploits
artificial intelligence, integrates current and
historical AIS positions as well as multiple
data feeds and APIs. Such an effort would
require a world-class infrastructure. That’s
why we selected Neo4j.”
David Levy
Chief Marketing Officer
OrbitMI

61
AstraZeneca
Patient Journey
“We used graph algorithms to find
patients that had specific journey
types and patterns and then find
others that are close and similar.”
Joseph Roemer
Global Commercial IT Insight & Analytics Sr. Director
AstraZeneca
● Challenge: How to best intervene sooner for
complex diseases that develop over years
● Solution: Neo4j knowledge graph of 3 yrs of
visits, tests, & diagnosis with 10’s Bn of
records. Using graph algorithms and
machine learning together.
● Results:
○ Identified journey archetypes and
patterns using graph feature
engineering as input to ML
○ Revealed journey similarities over
time with community detection
○ Found influential touch-points in the
journey using graph algorithms

62
Neo4j working with Banking Circle to detect Fraud

63
Get started on your Graph Journey

Let’s wrap up….
● Graphs present the world how we know and learn it
● Graph Databases can handle vast amounts of data
● Detect implicit relationships and learn from your network structure
with Graph Data Science
● Next steps: try it out - use Neo4j Sandbox for your own
projects…and do not suffer in silence, let us help you!

66
(we)-[:value]->(relationships)

67
Thank you!
Contact us at:
hakan.lofqvist@neo4j.com
kristof.neys@neo4j.com
fredrik.johansson@neo4j.com

Keynote Presentation at GraphTalk Oslo 2023

Recommended

Recommended

More Related Content

Similar to Keynote Presentation at GraphTalk Oslo 2023

Similar to Keynote Presentation at GraphTalk Oslo 2023 (20)

More from Neo4j

More from Neo4j (20)

Recently uploaded

Recently uploaded (20)

Keynote Presentation at GraphTalk Oslo 2023