# Boosting Frequent Itemset Mining via Early Stopping Intersections

## TL;DR

This paper introduces a general early stopping technique to accelerate frequent itemset mining algorithms by detecting infrequent candidates sooner, significantly reducing runtime across various datasets.

## Contribution

The paper proposes a novel early-stopping criterion applicable to multiple frequent itemset mining algorithms, improving efficiency by early detection of infrequent candidates.

## Key findings

- Significant runtime reduction observed in experiments
- Effective across different datasets and algorithms
- Applicable to both TID-list and N-list based schemes

## Abstract

Mining frequent itemsets from a transaction database has emerged as a fundamental problem in data mining and committed itself as a building block for many pattern mining tasks. In this paper, we present a general technique to reduce support checking time in existing depth-first search generate-and-test schemes such as Eclat/dEclat and PrePost+. Our technique allows infrequent candidate itemsets to be detected early. The technique is based on an early-stopping criterion and is general enough to be applicable in many frequent itemset mining algorithms. We have applied the technique to two TID-list based schemes (Eclat/dEclat) and one N-list based scheme (PrePost+). Our technique has been tested over a variety of datasets and confirmed its effectiveness in runtime reduction.