IBM researchers are working with the Florida city to develop an application that detects patterns and activities from a variety of data sources.
Police in Fort Lauderdale, Fl., are working with IBM to harness advanced data and analytics tools to deter crime and better identify where to deploy resources.
The project, which began two weeks ago, will analyze a variety of complex big data sources, including 911 call records, crime data, special events information, public transportation routes, code enforcement and building permit activity. Data will be analyzed using a combination of advanced analytics technologies, including pattern recognition/discovery, factor/causality analysis and anomaly detection, according to James Lingerfelt, IBM public safety manager for Global Smarter Cities.
The IBM researchers are using analytics and dashboard technology to develop an application that goes well beyond just collecting information from criminal justice databases, Lingerfelt, a retired officer with the Washington, D.C., Metropolitan Police Department, told GCN. For example, information from other city departments about building permits and construction sites would alert officers that they might want to tighten security around new construction because of the likelihood of theft of building equipment.
Besides integrating data sources, the application allows police command and patrol officers to view information based on their roles. For instance, patrol officers can receive “be on the look out” reports of activity in their patrol area, such as a stolen car. The application can also tailor information to an officer’s specific role, such as a report that an ex-offender has been released back into the community.
“In a minute I can look at a screen and will know where I want to direct my attention,” Lingerfelt said. All of this information could not be assembled in one place before. Officers can document and adjust their priorities accordingly over time, he said.
The data analytics application will entirely change how Fort Lauderdale’s police department operates, Police Chief Frank Adderley said during an interview. “This will help speed up the investigation process and increase our ability to solve cases a lot quicker than we currently are,” he said.
It will also speed up follow-up investigations after crimes are reported. Information that used to take detectives four to seven days to collect will now be accessible to officers in the field within an hour, Adderley said. The pilot project will run until the end of the year; then the results will be evaluated and other police personnel will receive training before a full implementation of the program, he said.
The Fort Lauderdale project is part of the IBM First-of-a-Kind program, which brings together IBM researchers and clients to test new technologies on real business problems.
Other cities are deploying predictive analytics to prevent crime and improve public safety operations. New York City’s Office of Data Analytics built a “data bridge” to integrate data from 40 agencies and find previously unknown patterns and relationships for the city to follow up on. Over the past three years the analytics team has doubled the city’s hit rate in finding stores selling bootleg cigarettes, accelerated the removal of trees destroyed by Hurricane Sandy and directed housing and fire inspectors to structures that have been illegally sub-divided or are at risk of catching fire.
Other research projects are under way to add visual analytics to the police force’s crime fighting arsenal. For instance, Purdue University researchers have developed a tool that can give police and emergency responders a real-time view of a location, layered with crime, traffic, geospatial, weather and other data. The goal, researchers say, is to give law enforcement agencies predictive, as well as responsive, capabilities.