With the rapid rise of graph databases, organizations are now implementing advanced analytics and machine learning solutions to help drive business outcomes. This practical guide shows data scientists, data engineers, architects, and business analysts how to get started with a graph database using TigerGraph, one of the leading graph database models available.
You'll explore a three-stage approach to deriving value from connected data: connect, analyze, and learn. Victor Lee, Phuc Kien Nguyen, and Alexander Thomas present real use cases covering several contemporary business needs. By diving into hands-on exercises using TigerGraph Cloud, you'll quickly become proficient at designing and managing advanced analytics and machine learning solutions for your organization.
• Use graph thinking to connect, analyze, and learn from data for advanced analytics and machine learning
• Learn how graph analytics and machine learning can deliver key business insights and outcomes
• Use five core categories of graph algorithms to drive advanced analytics and machine learning
• Deliver a real-time 360-degree view of core business entities, including customer, product, service, supplier, and citizen
• Discover insights from connected data through machine learning and advanced analytics
Author(s): Victor Lee, Phuc Kien Nguyen, Alexander Thomas
Edition: 1
Publisher: O'Reilly Media
Year: 2023
Language: English
Commentary: Publisher's PDF
Pages: 314
City: Sebastopol, CA
Tags: Machine Learning; Unsupervised Learning; Cybersecurity; Graphs; Graph Data Model; Graph Algorithms; Fraud Detection; Investment; Transportation Models; Money Laundering; Graph Neural Networks; Graph Analytics; TigerGraph; Entity Resolution
Cover
Copyright
Table of Contents
Preface
Objectives
Audience and Prerequisites
Approach and Roadmap
Conventions Used in This Book
Using Code Examples
O’Reilly Online Learning
How to Contact Us
Acknowledgments
Chapter 1. Connections Are Everything
Connections Change Everything
What Is a Graph?
Why Graphs Matter
Edges Outperform Table Joins
Graph Analytics and Machine Learning
Graph-Enhanced Machine Learning
Chapter Summary
Part I. Connect
Chapter 2. Connect and Explore Data
Graph Structure
Graph Terminology
Graph Schemas
Traversing a Graph
Hops and Distance
Breadth and Depth
Graph Modeling
Schema Options and Trade-Offs
Transforming Tables in a Graph
Model Evolution
Graph Power
Connecting the Dots
The 360 View
Looking Deep for More Insight
Seeing and Finding Patterns
Matching and Merging
Weighing and Predicting
Chapter Summary
Chapter 3. See Your Customers and Business Better: 360 Graphs
Case 1: Tracing and Analyzing Customer Journeys
Solution: Customer 360 + Journey Graph
Implementing the C360 + Journey Graph: A GraphStudio Tutorial
Create a TigerGraph Cloud Account
Get and Install the Customer 360 Starter Kit
An Overview of GraphStudio
Design a Graph Schema
Data Loading
Queries and Analytics
Case 2: Analyzing Drug Adverse Reactions
Solution: Drug Interaction 360 Graph
Implementation
Graph Schema
Queries and Analytics
Chapter Summary
Chapter 4. Studying Startup Investments
Goal: Find Promising Startups
Solution: A Startup Investment Graph
Implementing a Startup Investment Graph and Queries
The Crunchbase Starter Kit
Graph Schema
Queries and Analytics
Chapter Summary
Chapter 5. Detecting Fraud and Money Laundering Patterns
Goal: Detect Financial Crimes
Solution: Modeling Financial Crimes as Network Patterns
Implementing Financial Crime Pattern Searches
The Fraud and Money Laundering Detection Starter Kit
Graph Schema
Queries and Analytics
Chapter Summary
Part II. Analyze
Chapter 6. Analyzing Connections for Deeper Insight
Understanding Graph Analytics
Requirements for Analytics
Graph Traversal Methods
Parallel Processing
Aggregation
Using Graph Algorithms for Analytics
Graph Algorithms as Tools
Graph Algorithm Categories
Chapter Summary
Chapter 7. Better Referrals and Recommendations
Case 1: Improving Healthcare Referrals
Solution: Form and Analyze a Referral Graph
Implementing a Referral Network of Healthcare Specialists
The Healthcare Referral Network Starter Kit
Graph Schema
Queries and Analytics
Case 2: Personalized Recommendations
Solution: Use Graph for Multirelationship-Based Recommendations
Implementing a Multirelationship Recommendation Engine
The Recommendation Engine 2.0 Starter Kit
Graph Schema
Queries and Analytics
Chapter Summary
Chapter 8. Strengthening Cybersecurity
The Cost of Cyberattacks
Problem
Solution
Implementing a Cybersecurity Graph
The Cybersecurity Threat Detection Starter Kit
Graph Schema
Queries and Analytics
Chapter Summary
Chapter 9. Analyzing Airline Flight Routes
Goal: Analyzing Airline Flight Routes
Solution: Graph Algorithms on a Flight Route Network
Implementing an Airport and Flight Route Analyzer
The Graph Algorithms Starter Kit
Graph Schema and Dataset
Installing Algorithms from the GDS Library
Queries and Analytics
Chapter Summary
Part III. Learn
Chapter 10. Graph-Powered Machine Learning Methods
Unsupervised Learning with Graph Algorithms
Learning Through Similarity and Community Structure
Finding Frequent Patterns
Extracting Graph Features
Domain-Independent Features
Domain-Dependent Features
Graph Embeddings: A Whole New World
Graph Neural Networks
Graph Convolutional Networks
GraphSAGE
Comparing Graph Machine Learning Approaches
Use Cases for Machine Learning Tasks
Pattern Discovery and Feature Extraction Methods
Graph Neural Networks: Summary and Uses
Chapter Summary
Chapter 11. Entity Resolution Revisited
Problem: Identify Real-World Users and Their Tastes
Solution: Graph-Based Entity Resolution
Learning Which Entities Are the Same
Resolving Entities
Implementing Graph-Based Entity Resolution
The In-Database Entity Resolution Starter Kit
Graph Schema
Queries and Analytics
Method 1: Jaccard Similarity
Merging
Method 2: Scoring Exact and Approximate Matches
Chapter Summary
Chapter 12. Improving Fraud Detection
Goal: Improve Fraud Detection
Solution: Use Relationships to Make a Smarter Model
Using the TigerGraph Machine Learning Workbench
Setting Up the ML Workbench
Working with ML Workbench and Jupyter Notes
Graph Schema and Dataset
Graph Feature Engineering
Training Traditional Models with Graph Features
Using a Graph Neural Network
Chapter Summary
Connecting with You
Index
About the Authors
Colophon
