Next-Generation Recommendation Systems : A Comprehensive Guide to Enabling Technologies and Tools and Their Business Benefits

• Autore: Chelliah Pethuru Raj
• Pubblicazione: Newark : , : John Wiley & Sons, Incorporated, , 2026; ©2026
• Edizione: 1st ed.
• Descrizione fisica: 1 online resource (642 pages)
• Disciplina: 006.35
• Soggetto topico: Recommender systems (Information filtering)
• Nota di contenuto: Cover -- Title Page -- Copyright -- Contents -- About the Editors -- List of Contributors -- Chapter 1 Describing Decisive Digital Transformation Technologies and Tools -- 1.1 Introduction -- 1.1.1 Evolution of Recommendation Systems -- 1.1.2 Impact of Digital Transformation -- 1.1.3 Chapter Overview and Objectives -- 1.2 Core Infrastructure Technologies -- 1.2.1 Cloud Computing Platforms -- 1.2.2 Microservices Architecture -- 1.2.3 Edge Computing Solutions -- 1.2.4 Data Storage and Processing Systems -- 1.3 Development Frameworks and Tools -- 1.3.1 MLOps Frameworks -- 1.3.2 DevOps Integration -- 1.3.3 Model Development Tools -- 1.3.4 Testing and Validation Frameworks -- 1.4 Real-Time Processing and Deployment -- 1.4.1 Stream Processing Technologies -- 1.4.2 Model Serving Platforms -- 1.4.3 Monitoring Solutions -- 1.4.4 Performance Optimization Tools -- 1.5 Implementation Strategies -- 1.5.1 System Architecture Design -- 1.5.2 Scalability Considerations -- 1.5.3 Security and Privacy Measures -- 1.5.4 Case Studies and Best Practices -- 1.6 Future Trends and Conclusions -- 1.6.1 Emerging Technologies -- 1.6.2 Industry Directions -- 1.6.3 Implementation Guidelines -- 1.6.4 Summary and Recommendations -- References -- Chapter 2 Delineating the Big Data Era and the Information Overload Problem -- 2.1 Introduction: The Twin Challenges of Big Data -- 2.2 Defining the Big Data Era -- 2.2.1 Characteristics of Big Data (The 5 Vs, and Potentially Others) -- 2.2.2 Driving Forces -- 2.3 The Nature of Information Overload in the Big Data Context -- 2.4 Psychological and Cognitive Impacts of Information Overload -- 2.4.1 Impact on Attention Span -- 2.4.2 Impact on Memory -- 2.4.3 Impact on Decision-Making Processes -- 2.4.4 Impact on Mental Health -- 2.5 Strategies and Technologies for Mitigation -- 2.5.1 Distributed Data Storage and Processing. ; 2.5.2 Data Filtering and Prioritization -- 2.5.3 Information Visualization and Summarization -- 2.5.4 Cloud Solutions -- 2.5.5 Intelligent Systems and AI-Driven Solutions -- 2.5.6 Information Management Strategies -- 2.6 Case Studies and Examples -- 2.7 Conclusion: Navigating the Information Deluge -- References -- Chapter 3 Expounding Collaborative Filtering-Based Recommendation System -- 3.1 Introduction -- 3.2 Methodology -- 3.2.1 Data Collection -- 3.2.2 Collaborative Filtering -- 3.2.3 Model Training and Evaluation -- 3.3 Results and Analysis -- 3.3.1 Top-Rated Items -- 3.3.2 User Preference Distribution -- 3.4 Types of Collaborative Filtering -- 3.5 Why Collaborative Filtering Is Used? -- 3.6 Advantages of Collaborative Filtering -- 3.7 Ethical Considerations in Recommendation Systems -- 3.7.1 Privacy Concerns -- 3.7.2 Bias and Fairness -- 3.7.3 Transparency and Explainability -- 3.8 Advanced Techniques in Collaborative Filtering -- 3.8.1 Matrix Factorization Methods -- 3.8.2 Singular Value Decomposition (SVD) -- 3.8.3 Deep Learning in Collaborative Filtering -- 3.8.4 Graph-Based Approaches -- 3.9 Challenges and Risks in Recommendation Systems -- 3.9.1 Cold Start Problem in Recommendation Systems -- 3.9.2 Scalability Challenges in Large-Scale Recommendation Systems -- 3.9.3 Cold Start Solutions and Hybrid Approaches -- 3.9.4 Overfitting in Recommendation Models -- 3.9.5 Handling Noisy and Inconsistent Data -- 3.10 System Architecture and Design -- 3.11 Machine Learning Models for Recommendation Systems -- 3.12 Performance Optimization Techniques -- 3.13 Database Design and Management -- 3.14 Implementing A/B Testing in User Experience Design -- 3.15 Scalability and Load Balancing Strategies -- 3.16 Design Thinking -- 3.16.1 The Five Stages of Design Thinking -- 3.17 What Tools Were Used? -- 3.18 How Design Thinking Affected this Chapter?. ; 3.19 Common Challenges in Design Thinking Implementation -- 3.20 How it has Been Solved? -- 3.21 Impact of Design Thinking on Customer Experience -- 3.22 Future Improvements Based on Inference -- 3.23 Conclusion -- References -- Chapter 4 Illuminating Knowledge Graph-Based Recommendation Solutions -- 4.1 Introduction -- 4.2 Foundations of Knowledge Graphs -- 4.2.1 Definition and Core Concepts -- 4.2.2 Components of a Knowledge Graph -- 4.2.2.1 Entities -- 4.2.2.2 Attributes -- 4.2.2.3 Relationships -- 4.2.3 Key Characteristics of Knowledge Graphs -- 4.2.4 Applications of Knowledge Graphs -- 4.3 Comparison with Traditional Databases -- 4.4 Examples of Real-World Knowledge Graphs -- 4.4.1 Google Knowledge Graph -- 4.4.2 Wikidata -- 4.4.3 Facebook Entity Graph -- 4.4.4 The Microsoft Academic Graph (MAG) -- 4.4.5 Amazon Product Knowledge Graph -- 4.5 KG-Based Recommendation Methodologies -- 4.5.1 Enhancing Collaborative Filtering with KGs -- 4.5.2 Improving Content-Based Filtering using KGs -- 4.5.3 Hybrid Approaches for Recommendation Systems -- 4.5.4 Graph Embeddings for Knowledge Graphs -- 4.5.4.1 Why Graph Embeddings are Important -- 4.5.4.2 Types of Graphs Embedding Methods -- 4.5.5 Deep Learning and Graph Neural Networks for KG-Based Recommendations -- 4.6 Real-World Applications of KG-Based Recommendations -- 4.6.1 E-Commerce and Personalized Shopping -- 4.6.2 Media Streaming and Content Discovery -- 4.6.3 Education and Skill-Based Learning Platforms -- 4.7 Challenges and Ethical Considerations in KG-Based Recommendations -- 4.7.1 Technical Challenge -- 4.7.2 Scalability and Computational Complexity -- 4.7.3 Data Bias and Fairness in Knowledge Graphs -- 4.7.4 Privacy Concerns and Regulatory Compliance -- References -- Chapter 5 Next Level Recommendation Systems: Harnessing the Power of GANs. ; 5.1 A Brief Overview of Generative Adversarial Networks -- 5.1.1 Key Mechanisms of GANs -- 5.1.1.1 Generator -- 5.1.1.2 Discriminator -- 5.1.1.3 Adversarial Process -- 5.1.1.4 Loss Functions -- 5.2 Catalytic Potential on GANs in Recommendation Systems -- 5.2.1 Handling Data Sparsity -- 5.2.2 Cold-Start Problem -- 5.2.3 Personalization and Diversity -- 5.2.4 Implicit Feedback Modeling -- 5.2.5 Cross-Domain Recommendations -- 5.2.6 Adversarial Training for Robustness -- 5.3 A Broader View on the Traditional Recommendation Systems -- 5.3.1 Collaborative Filtering (CF) -- 5.3.1.1 Types of Collaborative Filtering -- 5.3.1.2 Strengths of Collaborative Filtering -- 5.3.1.3 Limitations of Collaborative Filtering -- 5.3.2 Content-Based Filtering (CBF) -- 5.3.2.1 How Content-Based Filtering Works -- 5.3.2.2 Strengths of Content-Based Filtering -- 5.3.2.3 Limitations of Content-Based Filtering -- 5.3.3 Hybrid Approaches -- 5.3.3.1 Strengths of Hybrid Approaches -- 5.3.3.2 Limitations of Hybrid Approaches -- 5.4 Unique Strengths of GANs in Addressing the Limitations of Traditional Recommendation Systems -- 5.4.1 Handling Data Sparsity -- 5.4.1.1 Synthetic Data Generation -- 5.4.1.2 Enriched Training Data -- 5.4.2 Addressing the Cold-Start Problem -- 5.4.2.1 Synthetic User Profiles -- 5.4.2.2 Synthetic Item Representations -- 5.4.3 Enhancing Personalization and Diversity -- 5.4.3.1 Exploration of Latent Space -- 5.4.3.2 Novelty in Recommendations -- 5.4.4 Modeling Implicit Feedback -- 5.4.4.1 Noise Robustness -- 5.4.4.2 Refinement of Feedback -- 5.4.5 Cross-Domain Recommendations -- 5.4.5.1 Cross-Domain Interaction Generation -- 5.4.5.2 Transfer Learning -- 5.4.6 Adversarial Training for Robustness -- 5.4.6.1 Robustness to Attacks -- 5.4.7 Handling Non-Linear and Complex Relationships -- 5.4.7.1 Non-Linear Modeling -- 5.4.8 Scalability and Efficiency. ; 5.4.8.1 Efficient Data Generation -- 5.4.8.2 Parallel Processing -- 5.5 Key Architectures and Modifications of GAN for Recommendation Systems -- 5.5.1 Adversarial Personalized Ranking (APR) -- 5.5.1.1 Key Components of APR -- 5.5.1.2 Strengths of APR -- 5.5.1.3 Example Use Case -- 5.5.2 Collaborative GAN (CollaGAN) -- 5.5.2.1 Key Components of CollaGAN -- 5.5.2.2 Strengths of CollaGAN -- 5.5.2.3 Example Use Case -- 5.6 Other Notable GAN-Based Architectures for Recommendation Systems -- 5.6.1 IRGAN (Information Retrieval GAN) -- 5.6.2 Graph GAN -- 5.6.3 Causal GAN -- 5.7 Real-World Applications of GANs in E-Commerce, Streaming Platforms, and Personalized Marketing -- 5.7.1 Application in E-Commerce -- 5.7.1.1 Personalized Product Recommendations -- 5.7.1.2 Visual Search and Recommendation -- 5.7.1.3 Virtual Try-Ons -- 5.7.1.4 Practical Considerations -- 5.7.1.5 Ethical Concerns -- 5.7.2 Applications in Streaming Platforms -- 5.7.2.1 Personalized Content Recommendations -- 5.7.2.2 Content Generation -- 5.7.2.3 Enhanced User Engagement -- 5.7.2.4 Practical Considerations -- 5.7.2.5 Ethical Concerns -- 5.7.3 Applications in Personalized Marketing -- 5.7.3.1 Targeted Advertising -- 5.7.3.2 Customer Segmentation -- 5.7.3.3 Content Creation -- 5.7.3.4 Practical Considerations -- 5.7.3.5 Ethical Concerns -- 5.8 Future Directions in GAN-Based Recommendation Systems -- 5.8.1.1 Multi-Modal Data Integration -- 5.8.1.2 Enhanced User Profiling -- 5.8.1.3 Cross-Modal Recommendations -- 5.8.1.4 Context-Aware Recommendations -- 5.8.1.5 Challenges -- 5.8.2 Federated Learning -- 5.8.2.1 Privacy-Preserving Recommendations -- 5.8.2.2 Personalized Recommendations -- 5.8.2.3 Collaborative Filtering -- 5.8.2.4 Challenges -- 5.8.3 Explainable Recommendations -- 5.8.3.1 Interpretable User Profiles -- 5.8.3.2 Transparent Recommendations -- 5.8.3.3 Fairness and Bias Mitigation. ; 5.8.3.4 Challenges.
• Sommario/riassunto: A detailed guide to building cutting-edge recommendation systems In Next-Generation Recommendation Systems: A Comprehensive Guide to Enabling Technologies and Tools and their Business Benefits , a team of experienced technologists and educators, each with a proven track record in the field, delivers an expert guide to building robust.
• Titolo autorizzato: Next-Generation Recommendation Systems
• ISBN: 1-394-35157-7; 1-394-35156-9
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9911085127003321
• Lo trovi qui: Univ. Federico II