Spatiotemporal prediction of theft risk with deep inception-residual networks

Xinyue Ye, Lian Duan, Qiong Peng

Research output: Contribution to journalArticlepeer-review

12 Scopus citations


Spatiotemporal prediction of crime is crucial for public safety and smart cities operation. As crime incidents are distributed sparsely across space and time, existing deep-learning methods constrained by coarse spatial scale offer only limited values in prediction of crime density. This paper proposes the use of deep inception-residual networks (DIRNet) to conduct fine-grained, theft-related crime prediction based on non-emergency service request data (311 events). Specifically, it outlines the employment of inception units comprising asymmetrical convolution layers to draw low-level spatiotemporal dependencies hidden in crime events and complaint records in the 311 dataset. Afterward, this paper details how residual units can be applied to capture high-level spatiotemporal features from low-level spatiotemporal dependencies for the final prediction. The effectiveness of the proposed DIRNet is evaluated based on theft-related crime data and 311 data in New York City from 2010 to 2015. The results confirm that the DIRNet obtains an average F1 of 71%, which is better than other prediction models.

Original languageEnglish (US)
Pages (from-to)204-216
Number of pages13
JournalSmart Cities
Issue number1
StatePublished - Mar 2021
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Electrical and Electronic Engineering
  • Urban Studies


  • Crime prediction
  • Deep convolution neural networks
  • Inception networks
  • New York City
  • Residual networks


Dive into the research topics of 'Spatiotemporal prediction of theft risk with deep inception-residual networks'. Together they form a unique fingerprint.

Cite this