Crime incidents embedding using restricted Boltzmann machines

TL;DR

This paper introduces an unsupervised learning approach using Gaussian-Bernoulli Restricted Boltzmann Machines to embed crime record narratives into a feature space, improving detection and clustering of related crime cases.

Contribution

The paper presents a novel application of RBMs for crime record embedding, incorporating narrative data beyond traditional time and location features.

Findings

Embeddings effectively cluster related crime incidents.

Unrelated cases are positioned far apart in the feature space.

Method shows promise in experiments with police-labeled data.

Abstract

We present a new approach for detecting related crime series, by unsupervised learning of the latent feature embeddings from narratives of crime record via the Gaussian-Bernoulli Restricted Boltzmann Machines (RBM). This is a drastically different approach from prior work on crime analysis, which typically considers only time and location and at most category information. After the embedding, related cases are closer to each other in the Euclidean feature space, and the unrelated cases are far apart, which is a good property can enable subsequent analysis such as detection and clustering of related cases. Experiments over several series of related crime incidents hand labeled by the Atlanta Police Department reveal the promise of our embedding methods.