International Journal of Engineering, Technology and Computer Science

TArtificial intelligence (AI) is transforming how libraries organize, curate, and recommend books by leveraging rich metadata, user behavior, and contextual signals to enhance discovery. Modern recommendation systems integrate collaborative filtering, content-based models, semantic relationships, and hybrid architectures to address challenges such as information overload, cold-start issues, and diverse user needs. High-quality catalog metadata, circulation records, user interaction logs, and enriched content features form the foundational data that support accurate, inclusive, and context-aware suggestions. Evaluation of these systems extends beyond accuracy to include novelty, user satisfaction, fairness, and privacy, acknowledging the ethical importance of transparency and equitable access. Implementation in library settings requires robust metadata standards, interoperable frameworks, skilled staff, and sufficient infrastructure. Public, academic, and special libraries adopt AI differently according to their operational goals, collections, and user communities. AI-driven book recommendations ultimately improve accessibility, promote serendipitous discovery, support research, and strengthen user engagement. Future work must refine data selection for infrequently circulated physical collections, improve user interfaces, and assess real-world patron perceptions to ensure responsible and effective deployment.