Abstract

The City of Chicago (with 50 wards) has one of the highest crime rates in the US. We seek to quantitatively assess the similarity of crime metrics across coterminous wards using a combination of Principal Component Analysis (PCA) and Assortativity analysis. We first build a ward network (nodes are the wards and edges connect coterminous wards) of the city using the ward map. We parse through the 2022 crime dataset for the city and build a matrix whose entries correspond to the number of occurrences of a crime type in a ward. We conduct PCA of this ward-crime type matrix and determine a weighted average PC_crime_score (using the entries in the high-variance principal components and their variances as weights) for each ward. We observe the coterminous wards to exhibit moderate-strong assortativity with respect to three different crime metrics: hotspot classification, PC_crime_scores and the crime counts of the individual crime types.

This work is licensed under a Creative Commons Attribution 4.0 License.