Graph-Powered Analytics and Machine Learning with TigerGraph

Table of contents

1. Preface
   1. Objectives
   2. Audience and Prerequisites
   3. Approach and Roadmap
   4. Conventions Used in This Book
   5. Using Code Examples
   6. O’Reilly Online Learning
   7. How to Contact Us
   8. Acknowledgments
2. 1. Connections Are Everything
   1. Connections Change Everything
      1. What Is a Graph?
      2. Why Graphs Matter
      3. Edges Outperform Table Joins
   2. Graph Analytics and Machine Learning
      1. Graph-Enhanced Machine Learning
   3. Chapter Summary
3. I. Connect
4. 2. Connect and Explore Data
   1. Graph Structure
      1. Graph Terminology
      2. Graph Schemas
   2. Traversing a Graph
      1. Hops and Distance
      2. Breadth and Depth
   3. Graph Modeling
      1. Schema Options and Trade-Offs
      2. Transforming Tables in a Graph
      3. Model Evolution
   4. Graph Power
      1. Connecting the Dots
      2. The 360 View
      3. Looking Deep for More Insight
      4. Seeing and Finding Patterns
      5. Matching and Merging
      6. Weighing and Predicting
   5. Chapter Summary
5. 3. See Your Customers and Business Better: 360 Graphs
   1. Case 1: Tracing and Analyzing Customer Journeys
   2. Solution: Customer 360 + Journey Graph
   3. Implementing the C360 + Journey Graph: A GraphStudio Tutorial
      1. Create a TigerGraph Cloud Account
      2. Get and Install the Customer 360 Starter Kit
      3. An Overview of GraphStudio
      4. Design a Graph Schema
      5. Data Loading
      6. Queries and Analytics
   4. Case 2: Analyzing Drug Adverse Reactions
   5. Solution: Drug Interaction 360 Graph
   6. Implementation
      1. Graph Schema
      2. Queries and Analytics
   7. Chapter Summary
6. 4. Studying Startup Investments
   1. Goal: Find Promising Startups
   2. Solution: A Startup Investment Graph
   3. Implementing a Startup Investment Graph and Queries
      1. The Crunchbase Starter Kit
      2. Graph Schema
      3. Queries and Analytics
   4. Chapter Summary
7. 5. Detecting Fraud and Money Laundering Patterns
   1. Goal: Detect Financial Crimes
   2. Solution: Modeling Financial Crimes as Network Patterns
   3. Implementing Financial Crime Pattern Searches
      1. The Fraud and Money Laundering Detection Starter Kit
      2. Graph Schema
      3. Queries and Analytics
   4. Chapter Summary
8. II. Analyze
9. 6. Analyzing Connections for Deeper Insight
   1. Understanding Graph Analytics
      1. Requirements for Analytics
      2. Graph Traversal Methods
      3. Parallel Processing
      4. Aggregation
   2. Using Graph Algorithms for Analytics
      1. Graph Algorithms as Tools
      2. Graph Algorithm Categories
   3. Chapter Summary
10. 7. Better Referrals and Recommendations
    1. Case 1: Improving Healthcare Referrals
    2. Solution: Form and Analyze a Referral Graph
    3. Implementing a Referral Network of Healthcare Specialists
       1. The Healthcare Referral Network Starter Kit
       2. Graph Schema
       3. Queries and Analytics
    4. Case 2: Personalized Recommendations
    5. Solution: Use Graph for Multirelationship-Based Recommendations
    6. Implementing a Multirelationship Recommendation Engine
       1. The Recommendation Engine 2.0 Starter Kit
       2. Graph Schema
       3. Queries and Analytics
    7. Chapter Summary
11. 8. Strengthening Cybersecurity
    1. The Cost of Cyberattacks
    2. Problem
    3. Solution
    4. Implementing a Cybersecurity Graph
       1. The Cybersecurity Threat Detection Starter Kit
       2. Graph Schema
       3. Queries and Analytics
    5. Chapter Summary
12. 9. Analyzing Airline Flight Routes
    1. Goal: Analyzing Airline Flight Routes
    2. Solution: Graph Algorithms on a Flight Route Network
    3. Implementing an Airport and Flight Route Analyzer
       1. The Graph Algorithms Starter Kit
       2. Graph Schema and Dataset
       3. Installing Algorithms from the GDS Library
       4. Queries and Analytics
    4. Chapter Summary
13. III. Learn
14. 10. Graph-Powered Machine Learning Methods
    1. Unsupervised Learning with Graph Algorithms
       1. Learning Through Similarity and Community Structure
       2. Finding Frequent Patterns
    2. Extracting Graph Features
       1. Domain-Independent Features
       2. Domain-Dependent Features
       3. Graph Embeddings: A Whole New World
    3. Graph Neural Networks
       1. Graph Convolutional Networks
       2. GraphSAGE
    4. Comparing Graph Machine Learning Approaches
       1. Use Cases for Machine Learning Tasks
       2. Pattern Discovery and Feature Extraction Methods
       3. Graph Neural Networks: Summary and Uses
    5. Chapter Summary
15. 11. Entity Resolution Revisited
    1. Problem: Identify Real-World Users and Their Tastes
    2. Solution: Graph-Based Entity Resolution
       1. Learning Which Entities Are the Same
       2. Resolving Entities
    3. Implementing Graph-Based Entity Resolution
       1. The In-Database Entity Resolution Starter Kit
       2. Graph Schema
       3. Queries and Analytics
       4. Method 1: Jaccard Similarity
       5. Merging
       6. Method 2: Scoring Exact and Approximate Matches
    4. Chapter Summary
16. 12. Improving Fraud Detection
    1. Goal: Improve Fraud Detection
    2. Solution: Use Relationships to Make a Smarter Model
    3. Using the TigerGraph Machine Learning Workbench
       1. Setting Up the ML Workbench
       2. Working with ML Workbench and Jupyter Notes
       3. Graph Schema and Dataset
       4. Graph Feature Engineering
       5. Training Traditional Models with Graph Features
       6. Using a Graph Neural Network
    4. Chapter Summary
    5. Connecting with You
17. Index
18. About the Authors