tppllm/chicago-crime-description

---
license: other
license_name: chicago-data-portal
license_link: https://portal.chicagopolice.org/portal/page/portal/ClearPath
language:
- en
size_categories:
- 1K<n<10K
---
# Chicago Crime Description Dataset

This dataset contains reported crime incidents in Chicago from January 1, 2022, to December 31, 2023. It includes 4,033 sequences with 202,333 events across 20 crime types. The data is sourced from the [Chicago Data Portal](https://data.cityofchicago.org/Public-Safety/Crimes-2001-to-Present/ijzp-q8t2) under the [Terms of Use](https://portal.chicagopolice.org/portal/page/portal/ClearPath). The detailed data preprocessing steps used to create this dataset can be found in the [TPP-LLM paper](https://arxiv.org/abs/2410.02062) and [TPP-LLM-Embedding paper](https://arxiv.org/abs/2410.14043).

If you find this dataset useful, we kindly invite you to cite the following papers:
```bibtex
@article{liu2024tppllmm,
title={TPP-LLM: Modeling Temporal Point Processes by Efficiently Fine-Tuning Large Language Models},
author={Liu, Zefang and Quan, Yinzhu},
journal={arXiv preprint arXiv:2410.02062},
year={2024}
}

@article{liu2024efficient,
title={Efficient Retrieval of Temporal Event Sequences from Textual Descriptions},
author={Liu, Zefang and Quan, Yinzhu},
journal={arXiv preprint arXiv:2410.14043},
year={2024}
}
```