# Crime Hot-Spot Modeling via Topic Modeling and Relative Density Estimation

arXiv: https://arxiv.org/abs/2202.04176 · HTML: https://mlsanity.com/paper/2202.04176/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 20 references that are in the map.
- First posted on arXiv 8 Feb 2022.

## Builds on (most cited first, 3 of 3)

- [The Why and How of Nonnegative Matrix Factorization](https://mlsanity.com/paper/1401.5226/) (2014)
- [Online Nonnegative Matrix Factorization with Outliers](https://mlsanity.com/paper/1604.02634/) (2016)
- [Crime Topic Modeling](https://mlsanity.com/paper/1701.01505/) (2017)

## Abstract (arXiv)

We present a method to capture groupings of similar calls and determine their relative spatial distribution from a collection of crime record narratives. We first obtain a topic distribution for each narrative, and then propose a nearest neighbors relative density estimation (kNN-RDE) approach to obtain spatial relative densities per topic. Experiments over a large corpus (n=475,019) of narrative documents from the Atlanta Police Department demonstrate the viability of our method in capturing geographic hot-spot trends which call dispatchers do not initially pick up on and which go unnoticed due to conflation with elevated event density in general.