Identifying potential trouble spots in prison facilities using analytics

Florida DOC turns to SAS to help ensure citizen safety

As one of the pillars of the state's criminal justice system, the Florida Department of Corrections (DOC) embraces a mission to protect the public and rehabilitate offenders by operating more than 50 major facilities housing more than 100,000 inmates and tracking an additional 145,000 offenders on various types of community supervision.

As a result of these extensive operations, the DOC collects vast amounts of information about its prison and community-supervision populations, including data on health, education, substance abuse programs, classes attended, tests taken, transfers within the prison system, court appearances, employment records, demographic data, attempted escapes, case notes, meetings with parole/probation officers and more.

The DOC supplements that data with additional information from other criminal justice agencies in the state to create the most comprehensive perspectives possible.

Dozens of data sources integrated

According to David Ensley, DOC's Research Director, a comprehensive reporting and analytics strategy driven by SAS has enabled the department to integrate dozens of disparate data sources from a variety of platforms.

"We have more than 100 scheduled data extracts every month," he explained. "These are simple jobs that bring the data to us in text files. We then use SAS to import that information into our data warehouse."

That's when a team of 16 SAS experts takes over, building a broad suite of standard statistical analyses and reports that are delivered to various stakeholders and requesters on an annual, quarterly, monthly and semimonthly basis.

Lawmakers get answers right away

The team responds to a constant flow of ad hoc requests that come from numerous sources: lawsuit discovery, the Governor's Office, state legislators, auditing agencies, federal officials, reporters, the general public and others.

These impromptu requests can range from a simple list to a complex question such as, "What is the recidivism rate for this subset of inmates who are enrolled in this specific program?"

"They all want answers right away," said Ensley. "So we need to be very responsive. These kinds of questions usually involve multiple SAS data sets that must be merged. Our team mostly creates these reports by writing code by hand in a simple editing window, although we're starting to use SAS to build some of the unique custom requests that involve multiple steps."

Inmates get the right interventions

One of the major challenges faced by the department is the allocation of scarce program resources to a huge inmate population in need of services.

To address this challenge, the DOC developed a risk and needs assessment tool called the Corrections Integrated Needs Assessment System. Its purpose is to identify inmates who are most in need of programs and ensure they receive priority ranking for program enrollment.

The DOC's research group also developed a model to predict inmate recidivism based on inmate characteristics captured in DOC databases. This model identifies higher-risk inmates who would benefit the most from program intervention. Survival analysis and logistic regression techniques in SAS were used to develop these models using data on thousands of inmates and hundreds of data elements.

Conditions monitored via dashboard

The DOC has applied similar concepts and approaches in analyzing inmate populations at the prison level. The Correctional Operational Trends and Analysis System analyzes a variety of factors to actually predict which facilities are at greater risk for disruptions such as escape attempts or inmate unrest.

"We've uncovered and statistically proven the correlations between disruptions and specific inmate characteristics, gang presence and other indicators," Ensley said.

"Based on our SAS analysis, our IT office turned that into a web-based dashboard that shows the condition of each facility using a stoplight interface. Then the user can drill down to see the risk factor behind that warning, such as a recent wave of new inmates belonging to gangs. With SAS, we have the right information to preserve citizen safety, allocate our resources more efficiently and report to our stakeholders."