Modeling Severe Traffic Accidents With Spatial And Temporal Features
This work addresses traffic safety policy-making by identifying key predictors of severe accidents, though it appears incremental in applying established machine learning methods to this domain.
The researchers tackled the problem of predicting traffic accident severity using spatial and temporal features from New York City data, finding that road network complexity and other features significantly improved prediction accuracy in both aggregated and disaggregated models.
We present an approach to estimate the severity of traffic related accidents in aggregated (area-level) and disaggregated (point level) data. Exploring spatial features, we measure complexity of road networks using several area level variables. Also using temporal and other situational features from open data for New York City, we use Gradient Boosting models for inference and measuring feature importance along with Gaussian Processes to model spatial dependencies in the data. The results show significant importance of complexity in aggregated model as well as as other features in prediction which may be helpful in framing policies and targeting interventions for preventing severe traffic related accidents and injuries.