HiPaR: Hierarchical Pattern-aided Regression

TL;DR

HiPaR is a new pattern-aided regression method that combines pattern mining with local linear models to produce accurate, interpretable rules for tabular data, outperforming existing methods in rule efficiency and prediction accuracy.

Contribution

It introduces a hybrid rule mining approach that efficiently explores data regions and combines pattern mining with local linear regression for improved interpretability and performance.

Findings

Fewer rules are mined compared to existing methods.

Achieves state-of-the-art prediction accuracy.

Provides more human-readable hybrid rules.

Abstract

We introduce HiPaR, a novel pattern-aided regression method for tabular data containing both categorical and numerical attributes. HiPaR mines hybrid rules of the form $p \Rightarrow y = f(X)$ where $p$ is the characterization of a data region and $f(X)$ is a linear regression model on a variable of interest $y$. HiPaR relies on pattern mining techniques to identify regions of the data where the target variable can be accurately explained via local linear models. The novelty of the method lies in the combination of an enumerative approach to explore the space of regions and efficient heuristics that guide the search. Such a strategy provides more flexibility when selecting a small set of jointly accurate and human-readable hybrid rules that explain the entire dataset. As our experiments shows, HiPaR mines fewer rules than existing pattern-based regression methods while still attaining state-of-the-art prediction performance.