Machine Learning for Database Management and Query Optimization

Abstract

In the present day, Traditional database management methods are becoming more inadequate for effective data processing as the volume of data created by systems grows. Machine learning approaches have shown promise in optimizing database queries and enhancing database administration functions such as query optimization, workload management, indexing, and data quality assurance to solve this problem. We investigate the different machine learning algorithms used for query optimization and database management in this comprehensive literature review. Our review shows that machine learning approaches such as Deep Learning (DL), Reinforcement learning (RL), supervised learning, natural language processing (NLP), and unsupervised learning, among others, may be employed for query analysis, execution, and assessment. It is feasible to increase query performance and react to changing conditions by introducing machine learning techniques into database management systems.