Abstract

The current thesis examines the application of Artificial Intelligence (AI) in the arena of predictive policing and crime forecasting using an integrated case study based on the empirical approach supported by a narrative review of literature. Due to the growing use of digital data by the law-enforcement agencies, AI techniques, including machine learning and spatio-temporal modelling, are implemented to detect patterns of crimes, predict high-risk areas, and assist law-enforcement decision-making. Though these technologies have the potential to make the processes of accuracy and resource allocation better, they also bring up the issue of the fairness, transparency, and disproportionate effects on the marginalised groups. In order to investigate these dynamics, this paper uses crime statistics of the City of Chicago and builds machine learning models to predict instances of assault using spatial and time characteristics. The results of the modelling show that advanced AI methods can have a high predictive performance, as compared to traditional baselines, especially in place-based forecasting. The Random Forest model was selected as the best performer, achieving a balanced F1-Score of 0.402 and a ROC AUC of 0.586, which indicates a moderate, non-random ability to identify crime hotspots. In addition to the empirical study, a narrative review of the current studies in criminology, data science, and public policy serves as an indicator of the existing controversies in the field of AI-enabled policing more specifically with regard to algorithmic bias and governance as well as accountability. In general, the results indicate that AI may have substantial analytical utility in the form of careful and context-specific application, but only when there are proper mechanisms of responsible implementation and efficient oversight. Instead of a solely technical problem, predictive policing turns out to be a socio-technical issue of governance, which requires the development of balanced systems to balance efficiency, fairness, and trust towards the government.

Publication Date

12-2025

Document Type

Thesis

Student Type

Graduate

Degree Name

Professional Studies (MS)

Department, Program, or Center

Graduate Programs & Research

Advisor

Sanjay Modak

Advisor/Committee Member

Ioannis Karamitsos

Campus

RIT Dubai

Download

Share

COinS