Recent advancements in crime prediction have increasingly focused on street networks, which offer finer granularity and a closer reflection of real-world urban dynamics. However, existing studies on street-level graph representation learning often overlook the variability in node features when aggregating information from neighboring nodes. This limitation reduces the model’s capacity to fully capture the diverse street attributes and their influence on crime patterns. To address this issue, we introduce an end-to-end deep spatio-temporal learning model that employs a graph attention mechanism (GAT) to analyze the spatio-temporal features of 110 call incidents. Experimental results show that our proposed model outperforms existing methods across multiple prediction metrics. Additionally, ablation studies confirm that the GAT’s capacity to capture spatial dependencies within the street network significantly enhances the model’s overall predictive performance.

In contemporary research, the street network emerges as a prominent and recurring theme in crime prediction studies. Meanwhile, graph representation learning shows considerable success, which motivates us to apply the methodology to crime prediction research. In this article, a graph representation learning approach is utilized to derive topological structure embeddings within the street network. Subsequently, a heterogeneous information network that incorporates both the street network and urban facilities is constructed, and embeddings through link prediction tasks are obtained. Finally, the two types of high-order embeddings, along with other spatio-temporal features, are fed into a deep neural network for street-level crime prediction. The proposed framework is tested using data from Beijing, and the outcomes demonstrate that both types of embeddings have a positive impact on crime prediction, with the second embedding showing a more significant contribution. Comparative experiments indicate that the proposed deep neural network offers superior efficiency in crime prediction.

Objective crime risk and perceived safety constitute distinct yet interrelated dimensions of urban security, whose spatial discrepancies may lead to misaligned policy interventions. This study develops a street-level analytical framework to examine the (mis)match between perceived safety and crime risk in Chaoyang District, Beijing. An enhanced Street-view imagery (SVI) segmentation model with object detection was applied to extract streetscape elements and estimate perceived safety scores, which were then standardized and compared with street-level crime data, yielding two types of matches and two types of mismatches. Three conditions were analyzed using multinomial logit regression: (1) objective unsafety with low perceived safety, (2) objective safety with low perceived safety, and (3) objective unsafety with high perceived safety. Findings demonstrate how visual and social environmental factors jointly shape discrepancies between perceived and actual safety and identify potential determinants to mitigate such (mis)matches.

Accurate crime spatiotemporal prediction is crucial for crime prevention. However, crime occurrences are influenced by diverse and interacting social factors, resulting in dynamically evolving distributions with non-stationarity and spatial heterogeneity. Most existing methods focus on data preprocessing or architectural enhancements and remain offline models, which limits their generalization capability. To address these challenges, we propose a novel spatial semantic-guided online learning framework. Specifically, we first compute the spatial semantic similarity between urban regions using points of interest. Based on this, we then introduce a contrastive learning objective guided by this similarity during training. This design aims to enhance the model’s ability to capture both the similarities and discrepancies among regions. During the prediction process, an iterative online learning strategy is employed to adapt to dynamically changing crime patterns. By continuously fine-tuning the model with streaming data, the proposed framework improves robustness and generalization under non-stationary crime spatiotemporal distributions. Finally, extensive experiments on real-world crime datasets indicate the effectiveness and stability of our proposed approach.