Background:

The purpose of the North Carolina Predictive Analytics Supervision Effort (NC PASE) was to use a data-driven approach to create supervision guidelines that will: decrease violations and increase compliance in the first six months; prevent early violations for Absconding/Public Safety, New Crime and Multiple Technical Violations; define “at risk” groups to increase engagement; and identify the supervision tool most needed based on the RNA priorities.

The Department of Public Safety partnered with George Mason University and the University of North Carolina at Chapel Hill to analyze a large administrative data set from 2017 that contained probation data for 57,710 people. The team then examined their probation violations and revocations within a two-year period to develop a better understanding of probation non-compliance and outcomes.

DPS representatives then used the findings to develop tailored supervision guidelines (TSGs). In addition, DPS representatives defined the overall supervision approach for TSGs, including: (1) early engagement, (2) prioritize supervision tools: services and consequences/controlling tools, (3) address barriers, (4) utilize incentives, and (5) respond to violations. Six counties in North Carolina were selected to implement these TSGs, which began in August of 2021.

Aims:

1) To use NCDPS data to develop an understanding of the predictors or “red flags” of probation non-compliance; and 2) to use NCDPS data to create and inform tailored Strategic Supervision Guidelines (SSG) to improve probation supervision practices and outcomes.

Using administrative data to model risk-need profiles and develop supervision guidelines to respond to these risk-need profiles has the potential to inform: 1) an understanding of the predictors or “red flags” of non-compliance; 2) the identification of risk-need profiles more prone to early non-compliance; and 3) the creation of tailored Strategic Supervision Guidelines (SSG) to improve and inform probation supervision plans.

Principal Investigators:

Tonya Van Deinse (PI)

Gary Cuddeback (Co-Investigator)

Articles:

Breno, A., Bhati, A., Van Deinse, T.B., Murphy, A., Cuddeback, G.S. & Taxman, F. (2023). Effective probation strategies to respond to signals of poor progress on community supervision. Criminal Justice & Behavior, 50(8), 1140-1162. https://doi.org/10.1177/00938548231165278