© 2022 Neo4j, Inc. All rights reserved.
© 2022 Neo4j, Inc. All rights reserved.
1
Dr. Jim Webber
Chief Scientist, Neo4j
Graph to the
Future!
© 2022 Neo4j, Inc. All rights reserved.
2
© 2022 Neo4j, Inc. All rights reserved.
Overview
• About Neo4j
• Intro to Graphs
• Neo4j Graph Platform
• RDBMS/NoSQL
• Graph Data Science
• Looking to the Future
© 2022 Neo4j, Inc. All rights reserved.
Neo4j: A Rich History of Graph Innovation
4
2020 - 2022
● Graph-RBAC Security, the First and
Most Advanced of Its Kind
● First Native & Fully Integrated Graph
Data Science Offering
● First In-Graph Machine Learning
Technology
● Neo4j Fabric, the First Enterprise
Graph Scaling Architecture for
Sharding & Federation
2015 - 2019
● openCypher: the De Facto Open
Source Graph Standard
● Graph Algorithms for Data Science
● Bloom for Rich Data Visualization and
Exploration
● Active Participant in ISO GQL
Standard, initiated by Neo4j
● AuraDB: First Native Graph DB as-a-
Service
2010 - 2014
● Pioneered the Graph Database Category
● First Native Graph Database:
Open Source, Built for Property Graphs
● Introduced Cypher Graph Query
Language
● Evolved Property Graph Model with
Labels, Geospatial & More
4
© 2022 Neo4j, Inc. All rights reserved.
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
5
© 2022 Neo4j, Inc. All rights reserved.
6
Since 2013
100m+ Neo4j Downloads
250k+ Community Members
Graph DB
Source: DB Engines
The Fastest Growing Database Market for a Decade
© 2022 Neo4j, Inc. All rights reserved.
The Graph Data Platform
Market Leader
1 Enterprises with >$1B annual revenue
2
Source: DBEngines
● HQ in Silicon Valley, with global footprint
● Over 300 global enterprise1
customers
800+ total customers
● Category creator and leader in Graph
Databases, the fastest growing category2 in
all of data management
Funding
$400M+
in 2021
~1000
Employees EOY
Growing at
50%+
YoY
2.5M+
Downloads
80%+
Active Developers YoY Growth
7
#1 Most Popular
Graph Database with Developers
200k+
Developers
© 2022 Neo4j, Inc. All rights reserved.
for Graph Data Platforms, Q4 2020
8
The Forrester Wave™
Neo4j: The Leader in a
Vibrant, Growing Market
8
© 2022 Neo4j, Inc. All rights reserved.
75+
Insurance
of the Top 10
8
Banks
of the Top 20
North American
20
Automakers
of the Top 10
8
Retailers
of the Top 10
7 Telcos
of the Top 10
7
Hotels
of the Top 5
3
Aircraft
Manufacturers
of the Top 5
3
Pharmaceuticals
of the Top 5
5
9
© 2022 Neo4j, Inc. All rights reserved.
10
Why Customers Choose Neo4j
Development & Data Science Agility
Developer Tooling
No-code, Built in query browser, data
visualizer
Data Science
Most graph algorithms,
Supervised ML
Standards & Open Source
GQL, OpenCypher
Cypher, GraphQL
Powerful, Intuitive, Flexible options
Battle Tested Foundation
Native Graph Architecture
Uncompromised Scale & Performance
Deep Domain Expertise
Category creator, Largest graph dev
investment, Focus
Largest Graph Community
250k+ developers and data scientists,
partners with leading CSPs and integrators.
Enterprise Proven, Trusted
1000s of deployments, powering global
brands
Proven Enterprise Performance, Scale, Security and Reliability
© 2022 Neo4j, Inc. All rights reserved.
© 2022 Neo4j, Inc. All rights reserved.
Hold on. What’s a
graph, Jim?
© 2022 Neo4j, Inc. All rights reserved.
12
But first…ground rules!
This
is
a
graph
This
is
a
chart
© 2022 Neo4j, Inc. All rights reserved.
13
You land here, at LHR
Neo4j London
© 2022 Neo4j, Inc. All rights reserved.
14
You land here, at LHR
Neo4j London
© 2022 Neo4j, Inc. All rights reserved.
15
You land here, at LHR
Neo4j London
© 2022 Neo4j, Inc. All rights reserved.
The Labeled Property Graph Model
Nodes
• Can have Labels to classify nodes
Relationships
• Relate nodes by type and direction
• Jim likes soccer, soccer does not like Jim
Properties
• Stored as name/value pairs
Performance
• Traversals are always O(1)
• Query latency depends on how much of the
graph you want to explore
• It does not depend on data set size
CAR
DRIVES
name: “Dan”
born: May 29, 1970
twitter: “@dan”
name: “Ann”
born: Dec 5, 1975
since:
Jan 10, 2011
brand: “Volvo”
model: “V70”
Latitude: 37.5629900°
Longitude: -122.3255300°
SISTER
BROTHER
O
W
N
S
PERSON PERSON
© 2022 Neo4j, Inc. All rights reserved.
1272 Pages
1 (widescreen) slide
© 2022 Neo4j, Inc. All rights reserved.
1272 Pages
OK, 209 pages
© 2022 Neo4j, Inc. All rights reserved.
© 2022 Neo4j, Inc. All rights reserved.
stole
from
loves
loves
enemy
enemy
A Good
Man Goes
to War
appeared
in
appeared
in
appeared
in
appeared
in
Victory of
the Daleks
appeared
in
appeared
in
companion
companion
enemy
© 2022 Neo4j, Inc. All rights reserved.
stole
from
loves
loves
enemy
enemy
A Good
Man Goes
to War
appeared
in
appeared
in
appeared
in
appeared
in
Victory of
the Daleks
appeared
in
appeared
in
companion
companion
enemy
planet
prop
species
species
species
character
character
character
episode
episode
© 2022 Neo4j, Inc. All rights reserved.
22
Modelling tip: use the Robinson* Algorithm
1. Write out the questions you
want to ask
2. Highlight/underline the nouns
3. Those are your nodes!
* Popularised by Mark Needham
http://www.markhneedham.com/blog/2013/11/29/neo4j-what-is-a-node/ @ianSrobinson
© 2022 Neo4j, Inc. All rights reserved.
© 2022 Neo4j, Inc. All rights reserved.
enemy
Victory of
the Daleks
appeared
in
appeared
in
companion
species character
character
episode
© 2022 Neo4j, Inc. All rights reserved. 25
25
Everything is around us is
Naturally Connected
© 2022 Neo4j, Inc. All rights reserved.
26
Higher Pay and More Promotions
• People Near Structural Holes
• Organizational Misfits
Network Structure is
Highly Predictive
Photo by Helena Lopes on Unsplash
“Organizational Misfits and the Origins of Brokerage in Intrafirm Networks” A. Kleinbaum
“Structural Holes and Good Ideas” R. Burt
© 2022 Neo4j, Inc. All rights reserved.
© 2022 Neo4j, Inc. All rights reserved.
27
Relationships
are the strongest
predictors of behavior
But You Can’t Analyse
What You Can’t See
● Most data science techniques
ignore relationships
● It’s painful to manually engineer
connected features from tabular
data
● Graphs are built on
relationships, so…
● You don’t have to guess at
the correlations: with graphs,
relationships are built in
James Fowler
© 2022 Neo4j, Inc. All rights reserved.
28
“Increasingly we’re learning
that you can make better
predictions about people by
getting all the information from
their friend and their friends’
friends than you can from the
information you have about the
person themselves.”
– Dr. James Fowler
© 2022 Neo4j, Inc. All rights reserved.
Static vs. Connected Data
A Paradigm Shift in How to Think About Data
© 2022 Neo4j, Inc. All rights reserved.
The Neo4j Graph Data Platform
Runs Anywhere
Deploy as-a-Service (AuraDB) or
self-hosted within your cloud of
choice (AWS, GCP, Azure) via their
marketplace, or on-premises.
Development Tools &
Frameworks
Tooling, APIs, query builder,
multi-language support for
development, admin, modeling,
and rapid prototyping needs.
Data Science and Analytics
Explorative tools, rich algorithm library,
and Integrated supervised Machine
Learning framework.
Native Graph Database
The foundation of the Neo4j platform;
delivers enterprise-scale and
performance, security, and data
integrity for transaction and analytical
workloads.
Graph Query Language
Cypher & openCypher; Ongoing
leadership and standards work (GQL)
to establish lingua franca for graphs.
Discovery & Visualization
Code-free querying, data modeling and
exploration tools for data scientists,
developers, and analysts.
Ecosystem & Integrations
Rich ecosystem of tech and
integration partners. Ingestion tools
(JDBC, Kafka, Spark, BI Tools, etc.) for
bulk and streaming needs.
30
© 2022 Neo4j, Inc. All rights reserved.
© 2022 Neo4j, Inc. All rights reserved.
31
NoSQL
RDBMS
• No connections
◦ Because heritage is
shopping baskets
• Documents, Columns are
rich, but stand in isolation
• Faking graph traversals via
indexes is expensive
• RDBMS is high fidelity
◦ But complex schema
operations
◦ And complex
denormalizations for
performance
• “Join bomb” problem
Established Data Models Hide the Problem
© 2022 Neo4j, Inc. All rights reserved.
32
30 Billion
1.2 Trillion!
128 Billion
Neo4j Fabric: Scaling Up & Scaling Out!
© 2022 Neo4j, Inc. All rights reserved.
© 2022 Neo4j, Inc. All rights reserved.
What about
analytics?
© 2022 Neo4j, Inc. All rights reserved.
What’s
Unusual?
What’s
Important?
What’s
Next?
Graph Data Science Helps
Make Sense of Your Data Relationships
34
Exploring the hidden patterns and features in your data
© 2022 Neo4j, Inc. All rights reserved.
35
Graphs Contain Implicit Knowledge
Which of the colored
nodes would be
considered the
most ‘important' ?
© 2022 Neo4j, Inc. All rights reserved.
36
Graph Algorithms Help Unlock This Knowledge
D
D has the highest valence
This is the most connected individual in the
network. If importance is how well you are
personally known you pick D.
G has the highest closeness centrality (0.52)
Information will disperse through the network
more quickly through this individual. If you need
to get a message out rapidly, choose them.
G
I has the highest betweenness centrality (0.59)
This person is an efficient connector of other people.
Risk of network disruption is higher if you lose this
individual.
I
Most Important?
© 2022 Neo4j, Inc. All rights reserved.
37
The Domains of Graph Data Science
Graph Native
Machine Learning
Learn features in your graph
that you don’t even know are
important yet using
embeddings.
Predict links, labels, and
missing data with in-graph
supervised ML models.
Identify associations,
anomalies, and trends using
unsupervised machine
learning.
Graph Algorithms
Knowledge Graphs
Find the patterns you’re looking
for in connected data
© 2022 Neo4j, Inc. All rights reserved.
38
The easiest graph
data science
platform
Easy to use
●Automated MLOps
●Runs Anywhere
●Cloud Commitments
Built by data
scientists, for data
scientists
Data Scientists
● Native Python Client
● 65+ Graph Algos
● ML Pipelines
Go to production
with speed, security,
and scale
Enterprise Ready
● 8M Objects/sec Load
● RBAC Security
● Designed to Scale
Fits into your data
stack and pipeline
Ecosystem
●BI tools, Apache Spark,
Kafka, Data Warehouses
●Vertex AI, SageMaker,
Synapse
Neo4j Graph Data Science
© 2022 Neo4j, Inc. All rights reserved.
The Neo4j Native Graph Catalog
• Automates data transformations
• Experiment with different data
sets, data models
• Fast iterations & layering
• Production ready features,
parallelization & enterprise
support
• Ability to persist and version
trained models
A graph-specific analytics workspace that’s mutable – integrated with Neo4j’s
native-graph database
Mutable In-Memory
Workspace
Graph Projection
Native Graph Store
© 2022 Neo4j, Inc. All rights reserved.
40
The Largest Catalog of Graph Algorithms
Pathfinding &
Search
Centrality &
Importance
Community
Detection
Supervised
Machine Learning
Heuristic Link
Prediction
Similarity Graph
Embeddings
…and more
Over 65 Pretuned, Parallelized Algorithms
© 2022 Neo4j, Inc. All rights reserved.
From Chaos to
Structure:
Neo4j Graph Data
Science is Changing
How Machine Learning
Gets Done
Graph Embeddings summarize the enhanced
explicit knowledge of a graph
41
© 2022 Neo4j, Inc. All rights reserved.
© 2022 Neo4j, Inc. All rights reserved.
42
“50% of Gartner inquiries on the topic
of AI involve discussion of the use of
graph technology.”
Top 10 Tech Trends in Data and Analytics 2021
AI Research Papers
Featuring Graph
Source: Dimensions Knowledge System
© 2022 Neo4j, Inc. All rights reserved.
43
Real World Data, Real World Fraud Detection
• Real, anonymized customer data set
• Using Neo4j Graph Data Science
• Blog post with sample code available
https://neo4j.com/developer-blog/exploring-fraud-detection-neo4j-graph-data-science-summary/
Exploring Fraud Detection With Neo4j &
Graph Data Science
Zach Blumenfeld
Data Science Product Specialist, Neo4j
87%
More fraud risks
detected!
© 2022 Neo4j, Inc. All rights reserved.
44
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
© 2022 Neo4j, Inc. All rights reserved.
New! Native Graph Data Science
Python Client
45
● Simplifies workflows for data scientists
● Run Graph Data Science algorithms just
like any Python function
● Eliminates the need for transaction
functions for data science
● Pythonic features support for graph and
model objects
© 2022 Neo4j, Inc. All rights reserved.
New! Explore Graph Algorithms Directly in Bloom
46
© 2022 Neo4j, Inc. All rights reserved.
47
New!
Graph Data Science
As-a-Service
● Handles all DB
management for you
● Simple to scale up or down
● Paused instance to save
● Starts at $1/hour
Enterprise ready, with fully
managed infrastructure,
updates, and security patches
© 2022 Neo4j, Inc. All rights reserved.
© 2022 Neo4j, Inc. All rights reserved.
Looking to the
future
© 2022 Neo4j, Inc. All rights reserved.
© 2022 Neo4j, Inc. All rights reserved.
49
“We are drowning
in information
but starved for
knowledge.”
John Naisbitt
Megatrends
© 2022 Neo4j, Inc. All rights reserved.
50
The Knowledge Lake Architecture
Knowledge Lake
Operational Data Stores
© 2022 Neo4j, Inc. All rights reserved.
© 2022 Neo4j, Inc. All rights reserved.
51
jim.webber@neo4j.com
Questions?

GraphSummit Toronto: Keynote - Innovating with Graphs

  • 1.
    © 2022 Neo4j,Inc. All rights reserved. © 2022 Neo4j, Inc. All rights reserved. 1 Dr. Jim Webber Chief Scientist, Neo4j Graph to the Future!
  • 2.
    © 2022 Neo4j,Inc. All rights reserved. 2
  • 3.
    © 2022 Neo4j,Inc. All rights reserved. Overview • About Neo4j • Intro to Graphs • Neo4j Graph Platform • RDBMS/NoSQL • Graph Data Science • Looking to the Future
  • 4.
    © 2022 Neo4j,Inc. All rights reserved. Neo4j: A Rich History of Graph Innovation 4 2020 - 2022 ● Graph-RBAC Security, the First and Most Advanced of Its Kind ● First Native & Fully Integrated Graph Data Science Offering ● First In-Graph Machine Learning Technology ● Neo4j Fabric, the First Enterprise Graph Scaling Architecture for Sharding & Federation 2015 - 2019 ● openCypher: the De Facto Open Source Graph Standard ● Graph Algorithms for Data Science ● Bloom for Rich Data Visualization and Exploration ● Active Participant in ISO GQL Standard, initiated by Neo4j ● AuraDB: First Native Graph DB as-a- Service 2010 - 2014 ● Pioneered the Graph Database Category ● First Native Graph Database: Open Source, Built for Property Graphs ● Introduced Cypher Graph Query Language ● Evolved Property Graph Model with Labels, Geospatial & More 4
  • 5.
    © 2022 Neo4j,Inc. All rights reserved. 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 5
  • 6.
    © 2022 Neo4j,Inc. All rights reserved. 6 Since 2013 100m+ Neo4j Downloads 250k+ Community Members Graph DB Source: DB Engines The Fastest Growing Database Market for a Decade
  • 7.
    © 2022 Neo4j,Inc. All rights reserved. The Graph Data Platform Market Leader 1 Enterprises with >$1B annual revenue 2 Source: DBEngines ● HQ in Silicon Valley, with global footprint ● Over 300 global enterprise1 customers 800+ total customers ● Category creator and leader in Graph Databases, the fastest growing category2 in all of data management Funding $400M+ in 2021 ~1000 Employees EOY Growing at 50%+ YoY 2.5M+ Downloads 80%+ Active Developers YoY Growth 7 #1 Most Popular Graph Database with Developers 200k+ Developers
  • 8.
    © 2022 Neo4j,Inc. All rights reserved. for Graph Data Platforms, Q4 2020 8 The Forrester Wave™ Neo4j: The Leader in a Vibrant, Growing Market 8
  • 9.
    © 2022 Neo4j,Inc. All rights reserved. 75+ Insurance of the Top 10 8 Banks of the Top 20 North American 20 Automakers of the Top 10 8 Retailers of the Top 10 7 Telcos of the Top 10 7 Hotels of the Top 5 3 Aircraft Manufacturers of the Top 5 3 Pharmaceuticals of the Top 5 5 9
  • 10.
    © 2022 Neo4j,Inc. All rights reserved. 10 Why Customers Choose Neo4j Development & Data Science Agility Developer Tooling No-code, Built in query browser, data visualizer Data Science Most graph algorithms, Supervised ML Standards & Open Source GQL, OpenCypher Cypher, GraphQL Powerful, Intuitive, Flexible options Battle Tested Foundation Native Graph Architecture Uncompromised Scale & Performance Deep Domain Expertise Category creator, Largest graph dev investment, Focus Largest Graph Community 250k+ developers and data scientists, partners with leading CSPs and integrators. Enterprise Proven, Trusted 1000s of deployments, powering global brands Proven Enterprise Performance, Scale, Security and Reliability
  • 11.
    © 2022 Neo4j,Inc. All rights reserved. © 2022 Neo4j, Inc. All rights reserved. Hold on. What’s a graph, Jim?
  • 12.
    © 2022 Neo4j,Inc. All rights reserved. 12 But first…ground rules! This is a graph This is a chart
  • 13.
    © 2022 Neo4j,Inc. All rights reserved. 13 You land here, at LHR Neo4j London
  • 14.
    © 2022 Neo4j,Inc. All rights reserved. 14 You land here, at LHR Neo4j London
  • 15.
    © 2022 Neo4j,Inc. All rights reserved. 15 You land here, at LHR Neo4j London
  • 16.
    © 2022 Neo4j,Inc. All rights reserved. The Labeled Property Graph Model Nodes • Can have Labels to classify nodes Relationships • Relate nodes by type and direction • Jim likes soccer, soccer does not like Jim Properties • Stored as name/value pairs Performance • Traversals are always O(1) • Query latency depends on how much of the graph you want to explore • It does not depend on data set size CAR DRIVES name: “Dan” born: May 29, 1970 twitter: “@dan” name: “Ann” born: Dec 5, 1975 since: Jan 10, 2011 brand: “Volvo” model: “V70” Latitude: 37.5629900° Longitude: -122.3255300° SISTER BROTHER O W N S PERSON PERSON
  • 17.
    © 2022 Neo4j,Inc. All rights reserved. 1272 Pages 1 (widescreen) slide
  • 18.
    © 2022 Neo4j,Inc. All rights reserved. 1272 Pages OK, 209 pages
  • 19.
    © 2022 Neo4j,Inc. All rights reserved.
  • 20.
    © 2022 Neo4j,Inc. All rights reserved. stole from loves loves enemy enemy A Good Man Goes to War appeared in appeared in appeared in appeared in Victory of the Daleks appeared in appeared in companion companion enemy
  • 21.
    © 2022 Neo4j,Inc. All rights reserved. stole from loves loves enemy enemy A Good Man Goes to War appeared in appeared in appeared in appeared in Victory of the Daleks appeared in appeared in companion companion enemy planet prop species species species character character character episode episode
  • 22.
    © 2022 Neo4j,Inc. All rights reserved. 22 Modelling tip: use the Robinson* Algorithm 1. Write out the questions you want to ask 2. Highlight/underline the nouns 3. Those are your nodes! * Popularised by Mark Needham http://www.markhneedham.com/blog/2013/11/29/neo4j-what-is-a-node/ @ianSrobinson
  • 23.
    © 2022 Neo4j,Inc. All rights reserved.
  • 24.
    © 2022 Neo4j,Inc. All rights reserved. enemy Victory of the Daleks appeared in appeared in companion species character character episode
  • 25.
    © 2022 Neo4j,Inc. All rights reserved. 25 25 Everything is around us is Naturally Connected
  • 26.
    © 2022 Neo4j,Inc. All rights reserved. 26 Higher Pay and More Promotions • People Near Structural Holes • Organizational Misfits Network Structure is Highly Predictive Photo by Helena Lopes on Unsplash “Organizational Misfits and the Origins of Brokerage in Intrafirm Networks” A. Kleinbaum “Structural Holes and Good Ideas” R. Burt
  • 27.
    © 2022 Neo4j,Inc. All rights reserved. © 2022 Neo4j, Inc. All rights reserved. 27 Relationships are the strongest predictors of behavior But You Can’t Analyse What You Can’t See ● Most data science techniques ignore relationships ● It’s painful to manually engineer connected features from tabular data ● Graphs are built on relationships, so… ● You don’t have to guess at the correlations: with graphs, relationships are built in James Fowler
  • 28.
    © 2022 Neo4j,Inc. All rights reserved. 28 “Increasingly we’re learning that you can make better predictions about people by getting all the information from their friend and their friends’ friends than you can from the information you have about the person themselves.” – Dr. James Fowler
  • 29.
    © 2022 Neo4j,Inc. All rights reserved. Static vs. Connected Data A Paradigm Shift in How to Think About Data
  • 30.
    © 2022 Neo4j,Inc. All rights reserved. The Neo4j Graph Data Platform Runs Anywhere Deploy as-a-Service (AuraDB) or self-hosted within your cloud of choice (AWS, GCP, Azure) via their marketplace, or on-premises. Development Tools & Frameworks Tooling, APIs, query builder, multi-language support for development, admin, modeling, and rapid prototyping needs. Data Science and Analytics Explorative tools, rich algorithm library, and Integrated supervised Machine Learning framework. Native Graph Database The foundation of the Neo4j platform; delivers enterprise-scale and performance, security, and data integrity for transaction and analytical workloads. Graph Query Language Cypher & openCypher; Ongoing leadership and standards work (GQL) to establish lingua franca for graphs. Discovery & Visualization Code-free querying, data modeling and exploration tools for data scientists, developers, and analysts. Ecosystem & Integrations Rich ecosystem of tech and integration partners. Ingestion tools (JDBC, Kafka, Spark, BI Tools, etc.) for bulk and streaming needs. 30
  • 31.
    © 2022 Neo4j,Inc. All rights reserved. © 2022 Neo4j, Inc. All rights reserved. 31 NoSQL RDBMS • No connections ◦ Because heritage is shopping baskets • Documents, Columns are rich, but stand in isolation • Faking graph traversals via indexes is expensive • RDBMS is high fidelity ◦ But complex schema operations ◦ And complex denormalizations for performance • “Join bomb” problem Established Data Models Hide the Problem
  • 32.
    © 2022 Neo4j,Inc. All rights reserved. 32 30 Billion 1.2 Trillion! 128 Billion Neo4j Fabric: Scaling Up & Scaling Out!
  • 33.
    © 2022 Neo4j,Inc. All rights reserved. © 2022 Neo4j, Inc. All rights reserved. What about analytics?
  • 34.
    © 2022 Neo4j,Inc. All rights reserved. What’s Unusual? What’s Important? What’s Next? Graph Data Science Helps Make Sense of Your Data Relationships 34 Exploring the hidden patterns and features in your data
  • 35.
    © 2022 Neo4j,Inc. All rights reserved. 35 Graphs Contain Implicit Knowledge Which of the colored nodes would be considered the most ‘important' ?
  • 36.
    © 2022 Neo4j,Inc. All rights reserved. 36 Graph Algorithms Help Unlock This Knowledge D D has the highest valence This is the most connected individual in the network. If importance is how well you are personally known you pick D. G has the highest closeness centrality (0.52) Information will disperse through the network more quickly through this individual. If you need to get a message out rapidly, choose them. G I has the highest betweenness centrality (0.59) This person is an efficient connector of other people. Risk of network disruption is higher if you lose this individual. I Most Important?
  • 37.
    © 2022 Neo4j,Inc. All rights reserved. 37 The Domains of Graph Data Science Graph Native Machine Learning Learn features in your graph that you don’t even know are important yet using embeddings. Predict links, labels, and missing data with in-graph supervised ML models. Identify associations, anomalies, and trends using unsupervised machine learning. Graph Algorithms Knowledge Graphs Find the patterns you’re looking for in connected data
  • 38.
    © 2022 Neo4j,Inc. All rights reserved. 38 The easiest graph data science platform Easy to use ●Automated MLOps ●Runs Anywhere ●Cloud Commitments Built by data scientists, for data scientists Data Scientists ● Native Python Client ● 65+ Graph Algos ● ML Pipelines Go to production with speed, security, and scale Enterprise Ready ● 8M Objects/sec Load ● RBAC Security ● Designed to Scale Fits into your data stack and pipeline Ecosystem ●BI tools, Apache Spark, Kafka, Data Warehouses ●Vertex AI, SageMaker, Synapse Neo4j Graph Data Science
  • 39.
    © 2022 Neo4j,Inc. All rights reserved. The Neo4j Native Graph Catalog • Automates data transformations • Experiment with different data sets, data models • Fast iterations & layering • Production ready features, parallelization & enterprise support • Ability to persist and version trained models A graph-specific analytics workspace that’s mutable – integrated with Neo4j’s native-graph database Mutable In-Memory Workspace Graph Projection Native Graph Store
  • 40.
    © 2022 Neo4j,Inc. All rights reserved. 40 The Largest Catalog of Graph Algorithms Pathfinding & Search Centrality & Importance Community Detection Supervised Machine Learning Heuristic Link Prediction Similarity Graph Embeddings …and more Over 65 Pretuned, Parallelized Algorithms
  • 41.
    © 2022 Neo4j,Inc. All rights reserved. From Chaos to Structure: Neo4j Graph Data Science is Changing How Machine Learning Gets Done Graph Embeddings summarize the enhanced explicit knowledge of a graph 41
  • 42.
    © 2022 Neo4j,Inc. All rights reserved. © 2022 Neo4j, Inc. All rights reserved. 42 “50% of Gartner inquiries on the topic of AI involve discussion of the use of graph technology.” Top 10 Tech Trends in Data and Analytics 2021 AI Research Papers Featuring Graph Source: Dimensions Knowledge System
  • 43.
    © 2022 Neo4j,Inc. All rights reserved. 43 Real World Data, Real World Fraud Detection • Real, anonymized customer data set • Using Neo4j Graph Data Science • Blog post with sample code available https://neo4j.com/developer-blog/exploring-fraud-detection-neo4j-graph-data-science-summary/ Exploring Fraud Detection With Neo4j & Graph Data Science Zach Blumenfeld Data Science Product Specialist, Neo4j 87% More fraud risks detected!
  • 44.
    © 2022 Neo4j,Inc. All rights reserved. 44 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
  • 45.
    © 2022 Neo4j,Inc. All rights reserved. New! Native Graph Data Science Python Client 45 ● Simplifies workflows for data scientists ● Run Graph Data Science algorithms just like any Python function ● Eliminates the need for transaction functions for data science ● Pythonic features support for graph and model objects
  • 46.
    © 2022 Neo4j,Inc. All rights reserved. New! Explore Graph Algorithms Directly in Bloom 46
  • 47.
    © 2022 Neo4j,Inc. All rights reserved. 47 New! Graph Data Science As-a-Service ● Handles all DB management for you ● Simple to scale up or down ● Paused instance to save ● Starts at $1/hour Enterprise ready, with fully managed infrastructure, updates, and security patches
  • 48.
    © 2022 Neo4j,Inc. All rights reserved. © 2022 Neo4j, Inc. All rights reserved. Looking to the future
  • 49.
    © 2022 Neo4j,Inc. All rights reserved. © 2022 Neo4j, Inc. All rights reserved. 49 “We are drowning in information but starved for knowledge.” John Naisbitt Megatrends
  • 50.
    © 2022 Neo4j,Inc. All rights reserved. 50 The Knowledge Lake Architecture Knowledge Lake Operational Data Stores
  • 51.
    © 2022 Neo4j,Inc. All rights reserved. © 2022 Neo4j, Inc. All rights reserved. 51 jim.webber@neo4j.com Questions?