Application of AI and Machine Learning in Query Optimization: Evolutionary Trends, Bibliometric Insights, and Framework Analysis

This paper provides a comprehensive review of the evolution of query optimization techniques, transitioning from traditional methods to Artificial Intelligence (AI) and Machine Learning (ML)-based approaches. The review bridges theoretical advancements with practical insights, offering researchers and practitioners a roadmap for adopting AI/ML-driven optimization in modern database systems. Employing a bibliometric analysis of Scopus database indexed publications from 2014 to 2024, the study maps research trends, key contributors, and thematic shifts in the field with the use of Biblioshiny and VOSViewer bibliometrics analysis tools. The study further systematically categorizes and evaluates state-of-the-art AI/ML frameworks focusing on their learning techniques, architectural models, and performance metrics. With China and the USA as the lead producers of articles relating to query optimization with AI/ML, the bibliometric analysis confirms rising interest and collaboration in this area. The annual scientific production shows an upward trend with 2024 being the highest record year with 2020–2022 year period serving as the transitional period the rise AI/ML query optimization related publications.