Improved Heterogeneous Distance Functions

TL;DR

This paper introduces three new heterogeneous distance functions that effectively handle datasets with both nominal and continuous attributes, improving classification accuracy over previous methods.

Contribution

The paper proposes three novel distance functions—HVDM, IVDM, and WVDM—that better manage mixed attribute types in instance-based learning.

Findings

Higher average classification accuracy on datasets with mixed attributes

Effective handling of continuous and nominal attributes without discretization

Improved performance over previous distance metrics

Abstract

Instance-based learning techniques typically handle continuous and linear input values well, but often do not handle nominal input attributes appropriately. The Value Difference Metric (VDM) was designed to find reasonable distance values between nominal attribute values, but it largely ignores continuous attributes, requiring discretization to map continuous values into nominal values. This paper proposes three new heterogeneous distance functions, called the Heterogeneous Value Difference Metric (HVDM), the Interpolated Value Difference Metric (IVDM), and the Windowed Value Difference Metric (WVDM). These new distance functions are designed to handle applications with nominal attributes, continuous attributes, or both. In experiments on 48 applications the new distance metrics achieve higher classification accuracy on average than three previous distance functions on those datasets that have both nominal and continuous attributes.