Interpretable Traffic Event Analysis with Bayesian Networks

TL;DR

This paper introduces an interpretable Bayesian Network framework for traffic accident analysis, enabling transparent understanding of how weather and traffic variables influence accident probabilities, aiding in accident reduction strategies.

Contribution

It presents a novel Bayesian Network-based approach with a dataset pipeline for interpretable traffic accident prediction and causal relationship analysis.

Findings

The framework predicts traffic accidents with competitive accuracy.

It reveals causal links between weather conditions and traffic events.

Visualization simplifies understanding of accident causes.

Abstract

Although existing machine learning-based methods for traffic accident analysis can provide good quality results to downstream tasks, they lack interpretability which is crucial for this critical problem. This paper proposes an interpretable framework based on Bayesian Networks for traffic accident prediction. To enable the ease of interpretability, we design a dataset construction pipeline to feed the traffic data into the framework while retaining the essential traffic data information. With a concrete case study, our framework can derive a Bayesian Network from a dataset based on the causal relationships between weather and traffic events across the United States. Consequently, our framework enables the prediction of traffic accidents with competitive accuracy while examining how the probability of these events changes under different conditions, thus illustrating transparent relationships between traffic and weather events. Additionally, the visualization of the network simplifies the analysis of relationships between different variables, revealing the primary causes of traffic accidents and ultimately providing a valuable reference for reducing traffic accidents.