SURVEY OF FRIEQUENT PATTERN SEARCH METHODS FOR DATA MINING

The article discusses one of the promlems of data mining, namely: the problem of searching for a special type of data dependencies - frequent patterns. Associative rules between features can be built on the basis of frequent patterns. A survey of the most popular methods for solving this problem is provided. The closely related problem of generating formal concepts based on a formal context is also considered, and one of the methods for solving it — the "close-by-one" method. The disadvantages of the considered methods include the complexity of their modification in the presence of additional (in addition to the frequency of occurrence in the training sample) requirements for the desired pattern. It is concluded that it is necessary to develop existing methods of pattern discovery, as well as the expediency of developing new approaches to solve the problems of searching for "interesting patterns", as well as searching for patterns with additional requirements for their type.