Generative AI for Next-Generation Recommender Systems: Architectures, Applications, and Future Directions

Title

Generative AI for Next-Generation Recommender Systems: Architectures, Applications, and Future Directions

Creator

Haseena, Shaik Valli; Jaswani, Neha

Description

The recommender systems have become a must in delivering personalized experiences across digital platforms. Still, traditional approaches, such as collaborative and content-based filtering, suffer from some inherent limitations: data sparsity, scalability, and dynamic user adaptation. In this context, generative AI emerges as a game-changing solution empowered by state-of-the-art models like variational autoencoders (VAEs), generative adversarial networks (GANs), and transformers to overcome the above-mentioned limitations. These models make possible the synthesis of user-item interaction data, uncovering latent patterns and providing context-aware recommendations, thereby redefining personalization in recommender systems. This chapter provides a detailed survey on the role of generative AI in recommender systems, their components, architectures, and applications. Case studies in e-commerce, entertainment, and education provide insights into how generative models help drive personalization, tackle the cold-start problem, and adapt dynamically to the evolution of user behaviors. Nevertheless, open issues regarding computational complexity, privacy protection, and ethical considerations remain. To address these, the chapter outlines the future enhancements in the areas of federated learning for privacy-preserving collaboration, multimodal data integration for holistic user profiling, and explainable AI frameworks to foster transparency and trust. Bridging these gaps would let generative AI-driven recommenders further revolutionize personalization, scalability, and inclusiveness, opening up a way to innovative solutions across the board in various industries. 2026 by John Wiley & Sons Inc. All rights reserved.

Source

Next-Generation Recommendation Systems: A Comprehensive Guide to Enabling Technologies and Tools and their Business Benefits;pp.201-223

Date

01-01-2026

Publisher

wiley

Subject

Data sparsity; Explainable AI; Federated learning; Generative adversarial networks; Generative AI; Personalization; Recommender systems; Transformers; Variational autoencoders

Coverage

Haseena S.V., Presidency College, Christ University, Bengaluru, India; Jaswani N., Presidency College, Bengaluru, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISBN: 978-139435157-2; 978-139435154-1;

Format

online

Language

English

Type

Book chapter

Identifier

https://doi.org/10.1002/9781394351572.ch9

https://www.scopus.com/pages/publications/105038510500?origin=resultslist