Authors: Gerhart Graupner*, , Kathy Kolnick, University of Southern California
Topics: Spatial Analysis & Modeling, Urban Geography
Keywords: crime analysis, spatial statistics, spatial modeling
Session Type: Paper
Start / End Time: 9:55 AM / 11:35 AM
Room: Wilson B, Marriott, Mezzanine Level
Presentation File: No File Uploaded
Los Angeles is a cosmopolitan megalopolis with an official population of 3.84 million persons in 2009. Lack of social cohesion is common in large and multicultural communities, facilitating different forms of “crimes of opportunity” in particular in neighborhoods of limited economic resources. Numerous neighborhoods in Los Angeles can be classified under this category. Gang activity as a second factor of promoting crime in Los Angeles is well documented, but its impact has been successfully reduced in recent years. To establish a robust reference set for the current dynamics in crime occurence, we present spatiotemporal changes of nonviolent and violent crimes documented in police records during the period of 2009 to 2013, using GIS technology and spatial statistics. We aim to determine whether the recent reduction in gang activity is also reflected in a different spatial pattern of violent crime. Furthermore, we aim to analyze whether a temporally stable “crime gradient” can be demonstrated for sites of non-violent crime that is defined by their closeness to the dense network of highways in Los Angeles. Our results will allow to test the quality of crime forecasting by a select set of current crime prediction algorithms, by comparing predictions based on the 2009-2013 dataset with the ground truth observed in 2014-2018.