Search Results for author: Zhengze Zhou

Found 6 papers, 3 papers with code

Examining spatial heterogeneity of ridesourcing demand determinants with explainable machine learning

no code implementations16 Sep 2022 Xiaojian Zhang, Xiang Yan, Zhengze Zhou, Yiming Xu, Xilei Zhao

The growing significance of ridesourcing services in recent years suggests a need to examine the key determinants of ridesourcing demand.

S-LIME: Stabilized-LIME for Model Explanation

1 code implementation15 Jun 2021 Zhengze Zhou, Giles Hooker, Fei Wang

An increasing number of machine learning models have been deployed in domains with high stakes such as finance and healthcare.

BIG-bench Machine Learning

$V$-statistics and Variance Estimation

1 code implementation2 Dec 2019 Zhengze Zhou, Lucas Mentch, Giles Hooker

This paper develops a general framework for analyzing asymptotics of $V$-statistics.

Distilling Black-Box Travel Mode Choice Model for Behavioral Interpretation

no code implementations30 Oct 2019 Xilei Zhao, Zhengze Zhou, Xiang Yan, Pascal Van Hentenryck

Furthermore, the paper provides a comprehensive comparison of student models with the benchmark model (decision tree) and the teacher model (gradient boosting trees) to quantify the fidelity and accuracy of the students' interpretations.

BIG-bench Machine Learning

Unbiased Measurement of Feature Importance in Tree-Based Methods

1 code implementation12 Mar 2019 Zhengze Zhou, Giles Hooker

We propose a modification that corrects for split-improvement variable importance measures in Random Forests and other tree-based methods.

Feature Importance

Approximation Trees: Statistical Stability in Model Distillation

no code implementations22 Aug 2018 Yichen Zhou, Zhengze Zhou, Giles Hooker

Here, we consider the use of regression trees as a student model, in which nodes of the tree can be used as `explanations' for particular predictions, and the whole structure of the tree can be used as a global representation of the resulting function.

Cannot find the paper you are looking for? You can Submit a new open access paper.