Data Driven Recommender systems: Methods and real-world applications

This book presents a comprehensive and up-to-date exploration of recommender systems, integrating foundational concepts with recent advancements in the field. It covers classical approaches such as collaborative filtering, content-based methods, and hybrid models, while also examining modern deep learning architectures including transformers and graph-based techniques. Emphasis is placed on evaluation metrics beyond accuracy—such as diversity, novelty, serendipity, and fairness—reflecting real-world system requirements. The book further addresses challenges in scalability, data sparsity, cold-start problems, and privacy-preserving approaches like federated learning. Through practical examples and case studies across domains such as e-commerce, healthcare, and social media, it provides a balanced perspective on both theoretical principles and applied system design.