Beyond Numbers: Integrating Expert Insights and Structured & Unstructured Data for Enhanced AI and Ml Predictive Models (PID055)

1.45pm – 2.20pm EDT, 22 April 2024 ‐ 35 mins

Room: Meeting Room 10

Parallel Workshop Session

AI offers unprecedented opportunities for improving the existing OMS. The efficacy of AI models is contingent on the quality and structure of the data they process. We will address the limitations of recidivism prediction methodologies (based on data stored in OMS). Traditional approaches largely focus on data and statistics collected during incarceration, overlooking the insights available from post-release data. This gap in data utilization hampers the accuracy and effectiveness of recidivism predictions, a cornerstone for informed decision-making in corrections. Our discussion will pivot towards the need for innovative data-driven strategies in digitization processes and will emphasize the integration of diverse digital systems, which can provide a more comprehensive data landscape. By integrating expert inputs and utilizing both structured and unstructured data from a myriad of sources, these systems can leverage advanced AI and ML algorithms to enhance decision-making processes.