Attention Based Stack ResNet for Citywide Traffic Accident Prediction

Abstract

The fine-grained citywide traffic accident prediction is of great significance for urban traffic management. Existing approaches mainly apply classic machine learning methods based on historical accident records. Thus they failed to involve the cross-domain data, which contains spatial and temporal dependency. Recently, with more cross-domain urban data available, leveraging the cross-domain data by deep learning algorithms to predict fine-grained accidents becomes possible, we propose an attention based ResNet framework to model the sophisticated correlation between urban data.