Abstract

Recidivism—the tendency of previously convicted individuals to reoffend—poses significant challenges to criminal justice systems worldwide. In the United States, a study by the Bureau of Justice Statistics revealed that approximately 68% of released prisoners were rearrested within three years, and 83% within nine years (Bureau of Justice Statistics, 2018). These high rates underscore systemic deficiencies in rehabilitation processes and resource allocation. Traditional risk assessment tools often rely on static factors, failing to account for the dynamic and individualized nature of reoffending risks. This limitation highlights the need for innovative, data-driven methodologies to enhance offender management strategies. This study proposes a framework that leverages advanced data analytics and predictive modeling to address these challenges. By integrating historical and real-time data, the framework aims to improve the accuracy of risk predictions, support dynamic monitoring, and enable the development of tailored intervention strategies. Techniques such as regression analysis and machine learning algorithms will be applied to identify key predictors of recidivism and assess the effectiveness of interventions. The framework emphasizes scalability and adaptability, ensuring applicability across various correctional and community supervision settings. A mixed-methods research design will guide the study. Quantitative techniques, including statistical modeling and machine learning, will analyze offender data and validate predictive models. Complementary qualitative methods, such as expert interviews and case studies, will provide contextual insights and ensure practical applicability. Legal and ethical considerations, including data privacy and algorithmic fairness, will be addressed to align the framework with principles of justice and proportionality. Anticipated outcomes include the development of a proactive offender management system that shifts focus from reactive responses to preventive measures. By optimizing resource allocation and delivering customized interventions, the framework aims to reduce recidivism rates while enhancing public safety and offender rehabilitation. The integration of data-driven approaches has the potential to empower policymakers, rehabilitation practitioners, and community supervision officers with tools to improve decision-making and resource management. This research contributes to the broader goal of creating a more equitable and efficient criminal justice system. It bridges gaps in current methodologies by applying advanced computational methods to offender management while addressing associated ethical challenges. Ultimately, the findings aim to support the development of systems that balance technological advancements with social and legal imperatives, fostering long-term societal benefits.

Library of Congress Subject Headings

Recidivism--Prevention--Data processing; Predictive analytics; Criminal justice, Administration of--Data processing; Restorative justice

Publication Date

5-2025

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

Plan Codes

PROFST-MS

Download

Share

COinS