Tuesday, July 21, 2009

Using BI to reduce the crime recidivism rate

I read in Information Management an interesting article about the use of data warehousing and business intelligence in an effort to reduce the recidivism rate in Washington, DC. The article, called The Tracker, written by John McCormick, shows how the Court Services and Offender Supervision Agency (CSOSA), the federal agency that manages probations and paroles in the nation's capital is using data warehousing and business intelligence in an intensive effort to reduce the city's recidivism rate and make its streets safer.

Two years ago, the percentage was 69 percent of the 15,000 offenders it supervises in a "successful posture". At present, the agency's goal is 80 percent, according to Calvin Johnson, CSOSA's director of the Office of Research and Evaluation.

In 2002, CSOSA built a case management system, which it calls the Supervision and Management Automated Record Tracking (SMART) system, based on a Microsoft's platform (SQL Server database and software developed in house). When SMART was first rolled out, they had some issues with data quality and data integrity. Another issue is the use of different BI tools from SAS, Business Objects and Microsoft by different offices.

In 2005, using the SAS 9 enterprise intelligence platform from the SAS Institute, Johnson's team deployed a data warehouse. The SMART case management system serves as the main source for the data warehouse. Data from local, state and federal law enforcement agencies is pulled into SMART and matched to the offenders in CSOSA's care.

The CSOSA also monitors in real time some 800 offenders ordered to wear GPS ankle devices. The data is transferred from the system to the CSOSA data warehouse over a secure FTP connection, giving CSOSA a high-level of visibility into the activities of those under house arrest.

For the future, CSOSA is looking to use its data warehouse and business intelligence tools to leverage predictive analytics in real time for decision support. Predictive analytics would give the agency the ability to conduct what-if analyses - plugging offender, behavior and historical reference data into the system to suggest a likely outcome to everyday activities.

The article describes an interesting real case. In the CSOSA's project, they had many common issues that happening in BI projects: data quality, data integrity, the use of many different tools by different offices, and still managed to implement a BI project successfully.

No comments: