A Comparative Study of Discretization Approaches for Granular Association Rule Mining

TL;DR

This paper investigates how different discretization methods, Equal Width and Equal Frequency, affect the quality and quantity of rules mined from numeric data in granular association rule mining, highlighting the importance of interval settings.

Contribution

It compares the impact of two discretization approaches on rule mining effectiveness and explores how interval settings influence rule generation in granular association rule mining.

Findings

Discretization improves rule strength in mining.

Equal Frequency yields more rules than Equal Width.

Interval settings significantly affect rule quantity.

Abstract

Granular association rule mining is a new relational data mining approach to reveal patterns hidden in multiple tables. The current research of granular association rule mining considers only nominal data. In this paper, we study the impact of discretization approaches on mining semantically richer and stronger rules from numeric data. Specifically, the Equal Width approach and the Equal Frequency approach are adopted and compared. The setting of interval numbers is a key issue in discretization approaches, so we compare different settings through experiments on a well-known real life data set. Experimental results show that: 1) discretization is an effective preprocessing technique in mining stronger rules; 2) the Equal Frequency approach helps generating more rules than the Equal Width approach; 3) with certain settings of interval numbers, we can obtain much more rules than others.