Time-Aware CrimeVec: Integrating Time2Vec for Spatio-Temporal Crime Embedding and Arrest Prediction

References

[1] H. Akaike, “Fitting autoregressive models for prediction,” Annals of the Institute of Statistical Mathematics, vol. 21, no. 1, pp. 243–247, 1969.

[2] R. N. Bracewell, The Fourier Transform and Its Applications. New York, NY, USA: McGraw-Hill, 1986.

[3] L. Cohen, Time-Frequency Analysis. Upper Saddle River, NJ, USA: Prentice Hall, 1995.

[4] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.

[5] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.

[6] A. Vaswani et al., “Attention is all you need,” in Advances in Neural Information Processing Systems (NeurIPS), 2017.

[7] A. Grover and J. Leskovec, “node2vec: Scalable feature learning for networks,” in Proc. ACM SIGKDD, 2016, pp. 855–864.

[8] I. M. Baytas et al., “Patient subtyping via time-aware LSTM networks,” in Proc. ACM SIGKDD, 2017, pp. 65–74.

[9] Y. Li, N. Du, and S. Bengio, “Time-dependent representation for neural event sequence prediction,” arXiv preprint arXiv:1708.00065, 2017.

[10] H. Mei and J. M. Eisner, “The neural Hawkes process: A neurally self-modulating multivariate point process,” in NeurIPS, 2017.

[11] A. Crivellari and A. Ristea, “CrimeVec—Exploring spatial-temporal based vector representations of urban crime types and crime-related urban regions,” ISPRS Int. J. Geo-Inf., vol. 10, no. 4, p. 210, 2021.

[12] U. M. Butt et al., “Spatio-temporal crime hotspot detection and prediction: A systematic literature review,” IEEE Access, vol. 8, pp. 166553–166574, 2020.

[13] Y. Du and N. Ding, “A systematic review of multi-scale spatio-temporal crime prediction methods,” ISPRS Int. J. Geo-Inf., vol. 12, no. 6, p. 209, 2023.

[14] Y. Qian et al., “GeST: A grid embedding based spatio-temporal correlation model for crime prediction,” in Proc. IEEE DSC, 2020, pp. 1–7.

[15] M. Hou et al., “An integrated graph model for spatial–temporal urban crime prediction based on attention mechanism,” ISPRS Int. J. Geo-Inf., vol. 11, no. 5, p. 294, 2022.

[16] W. Xu et al., “FIGAT: Accurately classify individual crime risks with multi-information fusion,” IEEE Trans. Services Computing, vol. 16, no. 3, pp. 1890–1903, 2022.

[17] M. Salcedo-Gonzalez et al., “Spatiotemporal predictive geo-visualization of criminal activity for real-time systems,” ISPRS Int. J. Geo-Inf., vol. 12, no. 7, p. 291, 2023.

[18] T. Wang, P. Chen, and M. Shan, “Crime spatiotemporal prediction through urban region representation using building footprints,” Big Data Cogn. Comput., vol. 9, no. 12, p. 301, 2025.

[19] U. M. Butt et al., “START: A spatiotemporal autoregressive transformer for enhancing crime prediction accuracy,” IEEE Trans. Computational Social Systems, 2025.

[20] Y. Guo, “Multimodal spatio-temporal fusion: A generalizable GCN-LSTM with attention framework for urban application,” Information Fusion, 2026.

@article{1717355,
      author = {Kancharla Puneeth Chowdary},
      title = {Time-Aware CrimeVec: Integrating Time2Vec for Spatio-Temporal Crime Embedding and Arrest Prediction},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {11},
      pages = {798-806},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1717355.pdf},
      abstract = {Crime analysis in urban areas is a critical component of community security and effective operation of law enforcement in cities today. Statistical summaries are used in most conventional methods of crime analysis. The episodes of crime are handled separately and do not indicate complex spatial and time associations among different types of crimes. Conventional data-driven approaches, e.g. criminal embedding techniques using Word2Vec, consider only the co-occurrence patterns, although generally not the temporal dynamics of the data, and as a result, are limited in prediction power. In order to address these limitations, in this paper, we present a novel Time-Aware CrimeVec (TA-CrimeVec) system that takes into consideration the temporal encoding and spatial-temporal crime embedding. The model is trained using Chicago Crime Dataset and uses Time2Vec to encode timestamps using linear and periodic functions. The criminal incidents are transformed to time-sensitive tokens and fed through a Skip-Gram based Word2Vec model to create hybrid embeddings that reflect crime type, time trends and spatial closeness. We then evaluate the learnt embeddings in predicting arrests with ML models like the RF and SVM. The results of the experiment demonstrate that the proposed method can attain a higher level of representation and prediction results, whereas the accuracy of the Random Forest is approximately 78.6 percent. The proposed solution is quite appropriate in capturing what happens when. It gives more information on the crime pattern and makes the decision making more informed in urban safety systems.},
      keywords = {Crime analysis, Time-Aware Embedding, CrimeVec, Time2Vec, Spatial-Temporal Modeling, Machine Learning.},
      month = {May},
      doi = {https://doi.org/10.64388/IREV9I11-1717355}
  }