Home » Case Studies » Epsilon Security Uses Statistics to Prevent Crime in Urban City Living


As changing lifestyles and demographics of urban populations fuel the rapid growth of high-density housing, understanding factors influencing the risk of crime occurrence in such buildings has become a vital tool for law enforcers. 

To tackle this problem, Epsilon Security teamed up with APR.Intern to place masters student, Puxue Qiao, and statistician Dr Davide Ferrari from the University of Melbourne, to establish a standard method in evaluating building crime rates through modelling which assess’ property risk and identifies safety solutions.

“Security systems have become a very important and integral part of both residential and commercial living and we have identified a gap in how the security of these buildings is managed,”


Andrea Baratta, Epsilon Security Managing Director

“The main concern is the lack of a standard method to evaluate security levels of buildings for comparisons. To do this we needed to develop a data-driven computer model to assess the security risk and potential crime exposure of a building,”


Andrea Baratta, Epsilon Security Managing Director

Puxue and Davide were able to take a step closer to achieving this, after building a generalised mixed-effect model. This type of model allowed them to make predictions of crime occurrences, whilst obtaining security ratings for each individual building.

The success of this project led the Epsilon Security team to apply for an ARC Linkage Projects grant to continue their work, with the objective of developing a fully automated tool for risk ratings in buildings.