Graph-Powered Machine Learning

Upgrade your machine learning models with graph-based algorithms, the perfect structure for complex and interlinked data.Summary In Graph-Powered Machine Learning, you will learn: The lifecycle of a machine learning project Graphs in big data platforms Data source modeling using graphs Graph-based natural language processing, recommendations, and fraud detection techniques Graph algorithms Working with Neo4J Graph-Powered Machine Learning teaches to use graph-based algorithms and data organization strategies to develop superior machine learning applications. You'll dive into the role of graphs in machine learning and big data platforms, and take an in-depth look at data source modeling, algorithm design, recommendations, and fraud detection. Explore end-to-end projects that illustrate architectures and help you optimize with best design practices. Author Alessandro Negro's extensive experience shines through in every chapter, as you learn from examples and concrete scenarios based on his work with real clients! Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications. About the technology Identifying relationships is the foundation of machine learning. By recognizing and analyzing the connections in your data, graph-centric algorithms like K-nearest neighbor or PageRank radically improve the effectiveness of ML applications. Graph-based machine learning techniques offer a powerful new perspective for machine learning in social networking, fraud detection, natural language processing, and recommendation systems. About the book Graph-Powered Machine Learning teaches you how to exploit the natural relationships in structured and unstructured datasets using graph-oriented machine learning algorithms and tools. In this authoritative book, you'll master the architectures and design practices of graphs, and avoid common pitfalls. Author Alessandro Negro explores examples from real-world applications that connect GraphML concepts to real world tasks. What's inside Graphs in big data platforms Recommendations, natural language processing, fraud detection Graph algorithms Working with the Neo4J graph database About the reader For readers comfortable with machine learning basics. About the author Alessandro Negro is Chief Scientist at GraphAware. He has been a speaker at many conferences, and holds a PhD in Computer Science. Table of Contents PART 1 INTRODUCTION 1 Machine learning and graphs: An introduction 2 Graph data engineering 3 Graphs in machine learning applications PART 2 RECOMMENDATIONS 4 Content-based recommendations 5 Collaborative filtering 6 Session-based recommendations 7 Context-aware and hybrid recommendations PART 3 FIGHTING FRAUD 8 Basic approaches to graph-powered fraud detection 9 Proximity-based algorithms 10 Social network analysis against fraud PART 4 TAMING TEXT WITH GRAPHS 11 Graph-based natural language processing 12 Knowledge graphs Graph-Powered Machine Learning brief content contents foreword preface acknowledgments about this book Who should read this book? How this book is organized About the code liveBook discussion forum Online resources about the author about the cover illustration Part 1: Introduction Chapter 1: Machine learning and graphs: An introduction 1.1 Machine learning project life cycle 1.1.1 Business understanding 1.1.2 Data understanding 1.1.3 Data preparation 1.1.4 Modeling 1.1.5 Evaluation 1.1.6 Deployment 1.2 Machine learning challenges 1.2.1 The source of truth 1.2.2 Performance 1.2.3 Storing the model 1.2.4 Real time 1.3 Graphs 1.3.1 What is a graph? 1.3.2 Graphs as models of networks 1.4 The role of graphs in machine learning 1.4.1 Data management 1.4.2 Data analysis 1.4.3 Data visualization 1.5 Book mental model Chapter 2: Graph data engineering 2.1 Working with big data 2.1.1 Volume 2.1.2 Velocity 2.1.3 Variety 2.1.4 Veracity 2.2 Graphs in the big data platform 2.2.1 Graphs are valuable for big data 2.2.2 Graphs are valuable for master data management 2.3 Graph databases 2.3.1 Graph database management 2.3.2 Sharding 2.3.3 Replication 2.3.4 Native vs. non-native graph databases 2.3.5 Label property graphs Chapter 3: Graphs in machine learning applications 3.1 Graphs in the machine learning workflow 3.2 Managing data sources 3.2.1 Monitor a subject 3.2.2 Detect a fraud 3.2.3 Identify risks in a supply chain 3.2.4 Recommend items 3.3 Algorithms 3.3.1 Identify risks in a supply chain 3.3.2 Find keywords in a document 3.3.3 Monitor a subject 3.4 Storing and accessing machine learning models 3.4.1 Recommend items 3.4.2 Monitoring a subject 3.5 Visualization 3.6 Leftover: Deep learning and graph neural networks Part 2: Recommendations Chapter 4: Content-based recommendations 4.1 Representing item features 4.2 User modeling 4.3 Providing recommendations 4.4 Advantages of the graph approach Chapter 5: Collaborative filtering 5.1 Collaborative filtering recommendations 5.2 Creating the bipartite graph for the User-Item dataset 5.3 Computing the nearest neighbor network 5.4 Providing recommendations 5.5 Dealing with the cold-start problem 5.6 Advantages of the graph approach Chapter 6: Session-based recommendations 6.1 The session-based approach 6.2 The events chain and the session graph 6.3 Providing recommendations 6.3.1 Item-based k-NN 6.3.2 Session-based k-NN 6.4 Advantages of the graph approach Chapter 7: Context-aware and hybrid recommendations 7.1 The context-based approach 7.1.1 Representing contextual information 7.1.2 Providing recommendations 7.1.3 Advantages of the graph approach 7.2 Hybrid recommendation engines 7.2.1 Multiple models, single graph 7.2.2 Providing recommendations 7.2.3 Advantages of the graph approach Part 3: Fighting fraud Chapter 8: Basic approaches to graph-powered fraud detection 8.1 Fraud prevention and detection 8.2 The role of graphs in fighting fraud 8.3 Warm-up: Basic approaches 8.3.1 Finding the origin point of credit card fraud 8.3.2 Identifying a fraud ring 8.3.3 Advantages of the graph approach Chapter 9: Proximity-based algorithms 9.1 Proximity-based algorithms: An introduction 9.2 Distance-based approach 9.2.1 Storing transactions as a graph 9.2.2 Creating the k-nearest neighbors graph 9.2.3 Identifying fraudulent transactions 9.2.4 Advantages of the graph approach Chapter 10: Social network analysis against fraud 10.1 Social network analysis concepts 10.2 Score-based methods 10.2.1 Neighborhood metrics 10.2.2 Centrality metrics 10.2.3 Collective inference algorithms 10.3 Cluster-based methods 10.4 Advantages of graphs Part 4: Taming text with graphs Chapter 11: Graph-based natural language processing 11.1 A basic approach: Store and access sequence of words 11.1.1 Advantages of the graph approach 11.2 NLP and graphs 11.2.1 Advantages of the graph approach Chapter 12: Knowledge graphs 12.1 Knowledge graphs: Introduction 12.2 Knowledge graph building: Entities 12.3 Knowledge graph building: Relationships 12.4 Semantic networks 12.5 Unsupervised keyword extraction 12.5.1 Keyword co-occurrence graph 12.5.2 Clustering keywords and topic identification 12.6 Advantages of the graph approach appendix A: Machine learning algorithms taxonomy A.1 Supervised vs. unsupervised learning A.2 Batch vs. online learning A.3 Instance-based vs. model-based learning A.4 Active vs. passive learning Reference appendix B: Neo4j B.1 Neo4j introduction B.2 Neo4j installation B.2.1 Neo4j server installation B.2.2 Neo4j Desktop installation B.3 Cypher B.4 Plugin installation B.4.1 APOC installation B.4.2 GDS Library B.5 Cleaning References appendix C: Graphs for processing patterns and workflows C.1 Pregel C.2 Graphs for defining complex processing workflows C.3 Dataflow References appendix D: Representing graphs References index A B C D E F G H I K L M N O P R S T U V W Identifying relationships is the foundation of machine learning. By recognizing and analyzing the connections in your data, graph-centric algorithms like K-nearest neighbor or PageRank radically improve the effectiveness of ML applications. Graph-based machine learning techniques offer a powerful new perspective for machine learning in social networking, fraud detection, natural language processing, and recommendiation systems. "Graph-powered machine learning" teaches you how to exploit the natural relationships in structured and unstructured datasets using graph-oriented machine learning algorithms and tools. In this authoritative book, you'll master the architectures and design practices of graphs, and avoid common pitfalls. Author Alessandro Negro explores examples from real-world applications that connect GraphML concepts to real world tasks At its core, machine learning is about efficiently identifying patterns and relationships in data. Many tasks, such as finding associations among terms so you can make accurate search recommendations or locating individuals within a social network who have similar interests, are naturally expressed as graphs. Graph-Powered Machine Learning introduces you to graph technology concepts, highlighting the role of graphs in machine learning and big data platforms. You’ll get an in-depth look at techniques including data source modeling, algorithm design, link analysis, classification, and clustering. As you master the core concepts, you’ll explore three end-to-end projects that illustrate architectures, best design practices, optimization approaches, and common pitfalls. Graph-Powered Machine Learning introduces you to graph technology concepts, highlighting the role of graphs in machine learning and big data platforms. Youll get an in-depth look at techniques including data source modeling, algorithm design, link analysis, classification, and clustering. As you master the core concepts, youll explore three end-to-end projects that illustrate architectures, best design practices, optimization approaches, and common pitfalls. Author Alessandro Negros extensive experience building graph-based machine learning systems shines through in every chapter, as you learn from examples and concrete scenarios based on his own work with real clients!