Enhanced Secondary Crash Classification through Functional Class-Based Weighting and Hybrid Machine Learning Models

Road safety and traffic management face significant challenges due to secondary crashes, which frequently cause more traffic, delays, and collisions. The importance of different types of roads is often overlooked by traditional methods for anticipating secondary crashes, which can result in suboptimal predictions and reaction plans. This research provides a novel method that combines a hybrid machine-learning model with a functional class-based weighting strategy to classify secondary crashes. The functional classes of the dataset are classified as interstates, arterial roads, collector roads, and local roads. The dataset also includes comprehensive crash narratives and various road attributes. Each functional class is assigned a weight that reflects its proportional importance in the likelihood of a subsequent crash, based on historical data and road usage patterns. After that, this weighting technique is integrated into a hybrid model architecture that trains a Random Forest model on structured data to make use of road-specific features and a Long Short-Term Memory (LSTM) network on crash narratives to capture the contextual and sequential information. A meta-classifier that incorporates the advantages of both methods combines these models to produce a more comprehensive forecast. The functional class-based weighting increases the model's sensitivity to high-risk road types—such as interstates and arterial roads—which are more likely to experience secondary crashes. By attaining greater precision, recall, and F1 scores than separate models, the hybrid model shows noticeably better performance. The findings show that combining functional class weights with hybrid models produced a 98% validation accuracy, which is essential information for traffic management. Transportation authorities may effectively manage secondary crash risks, allocate resources more efficiently, and improve overall road safety with this strategy.