Constrained frequent itemset mining from uncertain data streams


Frequent itemset mining is a common data mining task for many real-life applications. The mined frequent itemsets can be served as building blocks for various patterns including association rules and frequent sequences. Many existing algorithms mine for frequent itemsets from traditional static transaction databases, in which the contents of each transaction (namely, items) are definitely known and precise. However, there are many situations in which ones are uncertain about the contents of transactions. This calls for the mining of uncertain data. Moreover, there are also situations in which users are interested in only some portions of the mined frequent itemsets (i.e., itemsets satisfying user-specified constraints, which express the user interest). This leads to constrained mining. Furthermore, due to advances in technology, a flood of data can be produced in many situations. This calls for the mining of data streams. To deal with all these situations, we propose tree-based algorithms to efficiently mine streams of uncertain data for frequent itemsets that satisfy user-specified constraints.

DOI: 10.1109/ICDEW.2010.5452736

Extracted Key Phrases

3 Figures and Tables

Cite this paper

@article{Leung2010ConstrainedFI, title={Constrained frequent itemset mining from uncertain data streams}, author={Carson Kai-Sang Leung and Boyu Hao and Fan Jiang}, journal={2010 IEEE 26th International Conference on Data Engineering Workshops (ICDEW 2010)}, year={2010}, pages={120-127} }