A Review of Frequent Pattern Mining Algorithms for Uncertain Data

Abstract

Frequent pattern mining plays an essential role in data mining (e.g. finding association rules, correlation, sequences, and episodes). Uncertainty in data is generally caused by factors like data randomness and incompleteness, limitations of measuring equipment, delayed data updates, etc. Some of the important algorithms in finding all the frequent patterns from probabilistic datasets of uncertain data are U-Apriori, UF-growth, CUF-growth, PUF-growth. When users are only interested in some of the frequent patterns rather than all, these interests are expressed in terms of constraints and are pushed into mining process there by reducing search space. Finally big data era has brought challenges as well as tools for the problem of frequent pattern mining of uncertain data. In this paper all the above issues are briefly discussed and summarized.