Exploring the Determinants of Pedestrian Crash Severity Using an AutoML Approach

Amir Rafe, Patrick A. Singleton
6/7/2024
cs.LGcs.CY

No official code found. Best implementation: pozapas/CrashAutoML (2 stars, GPL-3.0, last commit 2024-06-14).

Abstract

This study investigates pedestrian crash severity through Automated Machine Learning (AutoML), offering a streamlined and accessible method for analyzing critical factors. Utilizing a detailed dataset from Utah spanning 2010-2021, the research employs AutoML to assess the effects of various explanatory variables on crash outcomes. The study incorporates SHAP (SHapley Additive exPlanations) to interpret the contributions of individual features in the predictive model, enhancing the understanding of influential factors such as lighting conditions, road type, and weather on pedestrian crash severity. Emphasizing the efficiency and democratization of data-driven methodologies, the paper discusses the benefits of using AutoML in traffic safety analysis. This integration of AutoML with SHAP analysis not only bolsters predictive accuracy but also improves interpretability, offering critical insights into effective pedestrian safety measures. The findings highlight the potential of this approach in advancing the analysis of pedestrian crash severity.

View on arXivView PDF

Code Implementations(1)

pozapas/CrashAutoMLCommunity100%
GPL-3.0

Crash Severity Analysis using Automated Machine Learning (AutoML) method

20Python, Jupyter NotebookDec 12, 20232 years agoGPL-3.0

Similar Papers

Exploring Factors Affecting Pedestrian Crash Severity Using TabNet: A Deep Learning Approach

89% match1 repo22023

Predicting and Explaining Traffic Crash Severity Through Crash Feature Selection

89% match2025

Unraveling Pedestrian Fatality Patterns: A Comparative Study with Explainable AI

88% match2025

Hotspot Prediction of Severe Traffic Accidents in the Federal District of Brazil

83% match2023

Exploring Traffic Crash Narratives in Jordan Using Text Mining Analytics

82% match2024

An Explainable Machine Learning Approach to Traffic Accident Fatality Prediction

82% match2024

Cite this paper

@article{rafe2024exploring,
  title  = {Exploring the Determinants of Pedestrian Crash Severity Using an AutoML Approach},
  author = {Amir Rafe and Patrick A. Singleton},
  year   = {2024},
  eprint = {2406.06624},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.06624v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.06624.svg)](https://codeofpaper.com/paper/2406.06624)

Discussion