Detecting Crime Series Based on Route Estimation and Behavioral Similarity

Abstract

Context. A majority of crimes are committed by a minority of offenders. Previous research has provided some support for the theory that serial offenders leave behavioral traces on the crime scene which could be used to link crimes to serial offenders. Objectives. Our objective was to investigate to what extent we could use route estimations and behavioral data to detect serial offenders. Method. To investigate if we could find crime routes with high similarity we ran experiments using behavioral data from authentic burglary reports. We also used used burglary reports from serial offenders to investigate to what extent we could detect serial offender crime routes. Results. The result show that crime series with the same offender on average had a higher behavioral similarity than random crime series. We also found crime series with high similarity without a known offender which could be interesting for law enforcement to investigate further. Conclusion. Our results suggest that it is possible to detect crime series committed by the same offender using behavioral data from the burglary. There is also potential for the law enforcement to detect interesting crime series with high similarity using behavioral similarity.

An interactive human centered data science approach towards crime pattern analysis

“…However, their approach does not deal with textual data. Researchers [30] developed an algorithm based on the modus operandi similarity of crime pattern using Jacquard coefficient to link burglaries to a serial offender. The result shows that crime series with the same offender on average had a higher behavioral similarity than random crime series.…”