k-NN algorithm, <filename>aqo</filename> improves cardinality estimation, which can optimize execution plans and, consequently, speed up query execution.

</para>

<para>The <filename>aqo</filename> module can collect statistics on all the executed

queries and classify it according to the query type. If the

queries, excluding the queries that access system relations.

The collected statistics is classified by query type. If the

queries differ in their constants only, they belong to the same

type. For each type, <filename>aqo</filename> stores the cardinality quality, planning

time, execution time, and execution statistics for machine learning. Based on this data, <filename>aqo</filename> builds a new query plan and uses it for the next query of the same type.