Explainable Machine Learning for Categorical and Mixed Data with Lossless Visualization

TL;DR

This paper introduces methods for encoding, visualizing, and explaining machine learning models on mixed categorical and numeric data, emphasizing lossless visualization and rule generation for interpretability.

Contribution

It develops numeric coding schemes, a toolkit for interpretability, and a new Sequential Rule Generation algorithm for explainable models on mixed data.

Findings

Successful evaluation of SRG algorithm in experiments

Effective lossless visualization of n-D categorical data

Enhanced interpretability of ML models on mixed data

Abstract

Building accurate and interpretable Machine Learning (ML) models for heterogeneous/mixed data is a long-standing challenge for algorithms designed for numeric data. This work focuses on developing numeric coding schemes for non-numeric attributes for ML algorithms to support accurate and explainable ML models, methods for lossless visualization of n-D non-numeric categorical data with visual rule discovery in these visualizations, and accurate and explainable ML models for categorical data. This study proposes a classification of mixed data types and analyzes their important role in Machine Learning. It presents a toolkit for enforcing interpretability of all internal operations of ML algorithms on mixed data with a visual data exploration on mixed data. A new Sequential Rule Generation (SRG) algorithm for explainable rule generation with categorical data is proposed and successfully evaluated in multiple computational experiments. This work is one of the steps to the full scope ML algorithms for mixed data supported by lossless visualization of n-D data in General Line Coordinates beyond Parallel Coordinates.