Feature Group Tabular Transformer: A Novel Approach to Traffic Crash Modeling and Causality Analysis
This provides an interpretable approach for road safety analysis, though it appears incremental as it adapts transformer architecture to tabular data for a specific domain.
This study tackled traffic crash modeling by developing a Feature Group Tabular Transformer (FGTT) to predict collision types from fused multi-source data, demonstrating superior predictive performance compared to tree ensemble models like Random Forest, XGBoost, and CatBoost.
Reliable and interpretable traffic crash modeling is essential for understanding causality and improving road safety. This study introduces a novel approach to predicting collision types by utilizing a comprehensive dataset fused from multiple sources, including weather data, crash reports, high-resolution traffic information, pavement geometry, and facility characteristics. Central to our approach is the development of a Feature Group Tabular Transformer (FGTT) model, which organizes disparate data into meaningful feature groups, represented as tokens. These group-based tokens serve as rich semantic components, enabling effective identification of collision patterns and interpretation of causal mechanisms. The FGTT model is benchmarked against widely used tree ensemble models, including Random Forest, XGBoost, and CatBoost, demonstrating superior predictive performance. Furthermore, model interpretation reveals key influential factors, providing fresh insights into the underlying causality of distinct crash types.