Data-Driven Predictive Modeling of Citywide Crowd Flow for Urban Safety Management: A Case Study of Beijing, China

Abstract

Crowd flow forecasting is vital for urban planning, resource allocation, and public safety, particularly in the context of the COVID-19 pandemic. However, traditional predictive models struggle to capture the complex, nonlinear spatial–temporal relationships inherent in crowd flow data due to its irregular volatility. To address these limitations, this paper proposes the innovative citywide crowd flow prediction (CCFP) model, which merges statistical rules with machine learning techniques (XGBoost, LightGBM, and CatBoost). The CCFP model is specifically designed to leverage spatial dependencies and two-level periodicity (weekly and daily) in population flow to predict crowd flow indexes ( $CFI$) within specific areas. We employ an urban area graph created using the Node2Vec algorithm to capture the temporal and spatial nuances of human flow patterns. Notably, this study innovatively incorporates migration, weather, and epidemic data into machine-learning models for feature extraction. Moreover, it introduces weighted factors— $growth,base,week$, and $day$—to enhance the accuracy of $CFI$ prediction. Among the combined models, CCFP outperforms others with remarkable scientific precision (root mean squared error, $RMSE=2.04$; mean absolute error, $MAE=0.81$; mean absolute percentage error, $MAPE=0.13$). Overall, the CCFP model represents a significant advancement in crowd flow prediction, offering valuable insights for urban safety management and city planning during pandemics.