A machine learning technique for monitoring database systems

A machine learning technique based database monitoring system is introduced. We report on a system which makes use of effective machine learning techniques to analyze user´s queries and make appropriate, valuable suggestions to the database administrator (DBA) to fine tune the performance of the database at hand. The system uses several machine learning algorithms to monitor the queries and attempt to extract commonalities exhibited by the queries. The concepts learnt are passed to another module of the system which will perform the restructuring of the database. We also report on the design and development of a carefully selected database application and the set of queries formed for the system.