Succinct Explanations With Cascading Decision Trees

TL;DR

This paper introduces Cascading Decision Trees, a new model that produces shorter, more interpretable decision paths, improves accuracy, and enhances robustness against missing data compared to traditional decision trees.

Contribution

The paper proposes Cascading Decision Trees, which separate decision and explanation paths, reducing path length and improving model robustness and accuracy.

Findings

Average 63.38% shorter explanation paths

Higher test accuracy compared to traditional trees

Improved robustness against missing values

Abstract

The decision tree is one of the most popular and classical machine learning models from the 1980s. However, in many practical applications, decision trees tend to generate decision paths with excessive depth. Long decision paths often cause overfitting problems, and make models difficult to interpret. With longer decision paths, inference is also more likely to fail when the data contain missing values. In this work, we propose a new tree model called Cascading Decision Trees to alleviate this problem. The key insight of Cascading Decision Trees is to separate the decision path and the explanation path. Our experiments show that on average, Cascading Decision Trees generate 63.38% shorter explanation paths, avoiding overfitting and thus achieve higher test accuracy. We also empirically demonstrate that Cascading Decision Trees have advantages in the robustness against missing values.