Mining Feature Relationships in Data

TL;DR

This paper introduces feature relationship mining (FRM), a genetic programming-based method for discovering interpretable symbolic relationships between features in continuous and categorical data, addressing limitations of traditional association rules.

Contribution

It presents the first symbolic approach for explicitly discovering feature relationships, applicable to continuous data, and demonstrates its effectiveness on real-world datasets.

Findings

Finds high-quality, simple feature relationships

Provides clear and non-trivial insights into data

Outperforms traditional association rule methods

Abstract

When faced with a new dataset, most practitioners begin by performing exploratory data analysis to discover interesting patterns and characteristics within data. Techniques such as association rule mining are commonly applied to uncover relationships between features (attributes) of the data. However, association rules are primarily designed for use on binary or categorical data, due to their use of rule-based machine learning. A large proportion of real-world data is continuous in nature, and discretisation of such data leads to inaccurate and less informative association rules. In this paper, we propose an alternative approach called feature relationship mining (FRM), which uses a genetic programming approach to automatically discover symbolic relationships between continuous or categorical features in data. To the best of our knowledge, our proposed approach is the first such symbolic approach with the goal of explicitly discovering relationships between features. Empirical testing on a variety of real-world datasets shows the proposed method is able to find high-quality, simple feature relationships which can be easily interpreted and which provide clear and non-trivial insight into data.