The Dynamic and Endogenous Behavior of Re-Offense Risk: An Agent-Based Simulation Study of Treatment Allocation in Incarceration Diversion Programs

2026-01-18

AI Summary

This study addresses a critical limitation in existing recidivism risk assessment tools, which treat risk as a static individual attribute and overlook its dynamic evolution and the endogenous effects of policy interventions mediated through social interactions. The authors propose a novel framework that conceptualizes recidivism risk as an emergent property of the dynamic interplay between individuals and the correctional system, thereby framing it for the first time as an endogenous sociotechnical phenomenon. Leveraging agent-based modeling (ABM), calibrated with U.S. probation data and evaluated through multi-scenario simulations under resource capacity constraints, the research systematically assesses alternative allocation strategies. Findings reveal no universally optimal policy: prioritizing low-risk individuals yields better outcomes over the long term, whereas focusing on high-risk individuals is superior in short-term or limited-supervision contexts, underscoring the need for risk-decision systems grounded in long-term accountability mechanisms.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Game Theory and Economic Paradigms: Mechanism Design
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Social and technical mechanisms of refusal for web technologies and applications
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Incarceration-diversion treatment programs aim to improve societal reintegration and reduce recidivism, but limited capacity forces policymakers to make prioritization decisions that often rely on risk assessment tools. While predictive, these tools typically treat risk as a static, individual attribute, which overlooks how risk evolves over time and how treatment decisions shape outcomes through social interactions. In this paper, we develop a new framework that models reoffending risk as a human-system interaction, linking individual behavior with system-level dynamics and endogenous community feedback. Using an agent-based simulation calibrated to U.S. probation data, we evaluate treatment allocation policies under different capacity constraints and incarceration settings. Our results show that no single prioritization policy dominates. Instead, policy effectiveness depends on temporal windows and system parameters: prioritizing low-risk individuals performs better when long-term trajectories matter, while prioritizing high-risk individuals becomes more effective in the short term or when incarceration leads to shorter monitoring periods. These findings highlight the need to evaluate risk-based decision systems as sociotechnical systems with long-term accountability, rather than as isolated predictive tools.

Problem

• recidivism risk
• dynamic risk
• endogenous behavior
• treatment allocation
• incarceration diversion

Innovation

• agent-based simulation
• dynamic risk modeling
• endogenous feedback
• treatment allocation
• recidivism prediction