Since the introduction of the Frequent Itemset Mining (FIM) problem, several different algorithms for solving it were proposed and experimentally analyzed. Our work focusses on the theoretical analysis of FIM. The aim is to give a detailed probabilistic study of the performance of FIM algorithms for different data distributions. It is joint work with Dirk Van Gucht and Paul Purdom from Indiana ...

Data mining is the process of extracting useful unknown knowledge from large datasets. Frequent itemset fundamental task data that aims at discovering interesting itemsets frequently appear together in a dataset. However, infrequent (rare) may be more many real-life applications such as predicting telecommunication equipment failures, genetics, medical diagnosis, or anomaly detection. In this p...