Decision Tree Approach to Accident Prediction for Highway–Rail Grade Crossings: Empirical Analysis

Abstract

Highway–rail grade crossings (HRGCs) are critical spatial locations that are of utmost importance for transportation safety because traffic crashes at these locations are often catastrophic. Compared with traditional regression models, the decision tree is more advanced in its ability to handle large data sets, deal with missing values, and not require predefined underlying relationships between target variables and predictors. Thus the decision tree approach is explored in this study, which evaluates HRGC crashes. Because crashes at HRGCs are rare, the majority of data will have a zero-crash classification. A traditional decision tree method will have a bias toward the majority classification, which will result in a good prediction for the majority class but a relatively poor prediction for rare events. To improve model accuracy with the decision tree model, especially for forecasting rare events, previous probability and decision profit values are adjusted. Historical crash data of North Dakota State from 1996 to 2014 are analyzed, and factors relevant to HRGC crashes are investigated. Results reveal that 23 variables are considered as contributors to crashes at highway–rail crossings. Results indicate that railway traffic, highway traffic, and train speed are main influential factors and have a positive impact on crash likelihood. Presence of train detecting and advance warning systems is helpful in reducing crash risk. Predicting accuracies of the model are 84.1% and 77.2% for event class and nonevent class, respectively.