An Efficient Rigorous Approach for Identifying Statistically Significant Frequent Itemsets

TL;DR

This paper introduces a rigorous and efficient method to determine a support threshold in frequent itemset mining, enabling the identification of statistically significant itemsets with controlled false discovery rate, validated through extensive experiments.

Contribution

A novel methodology for selecting support thresholds that distinguish significant itemsets from random noise in large datasets.

Findings

Effective identification of significant itemsets

Controlled false discovery rate achieved

Validated through extensive experiments

Abstract

As advances in technology allow for the collection, storage, and analysis of vast amounts of data, the task of screening and assessing the significance of discovered patterns is becoming a major challenge in data mining applications. In this work, we address significance in the context of frequent itemset mining. Specifically, we develop a novel methodology to identify a meaningful support threshold s* for a dataset, such that the number of itemsets with support at least s* represents a substantial deviation from what would be expected in a random dataset with the same number of transactions and the same individual item frequencies. These itemsets can then be flagged as statistically significant with a small false discovery rate. We present extensive experimental results to substantiate the effectiveness of our methodology.