Computer model anticipates crime hotspots

Researchers in the US working with a local police force have developed a computer model which they say than can anticipate crime hotspots. University of California, Riverside (UCR), sociologist Robert Nash Parker has provided the model to the police department in the city of Indio to help deploy officers in areas where crimes such as burglary are likely to occur.

The result has been an eight per cent drop in thefts in the first nine months of 2013.

The collaboration between Dr Parker, professor of sociology and senior researcher at UCR’s Presley Centre for Crime and Justice Studies, and Indio police is unusual, but it is the direction law enforcement is heading, said Indio Police Department (PD) Chief Richard Twiss.

“This is the wave of the future,” he said. “It is my hope this relationship with Dr Parker will continue throughout my tenure with this department, not only on this project, but with others as well.”

Dr Parker began working with the Indio PD in 2010 to determine if a computer model could predict by census block group – the smallest geographic unit the Census Bureau uses – where burglaries were most likely to occur.

“Thefts overall had been rising and I was concerned that we were on a course to exceed last year,” Police Chief Twiss said.

Using crime data and truancy records – truants account for a significant number of daytime burglaries – Dr Parker discovered patterns of crime over time and space. Most computer models account for changes over time or a variety of places, but not both.

“This is still cutting-edge and experimental,” Dr Parker explained. “Big Data gives you statistical power to make these kinds of predictions. It makes it possible for us to anticipate crime patterns, especially hotspots of crime, which allows law enforcement agencies to engage in targeted prevention activities that could disrupt the cause of crime before the crime happens.”

Dr Parker and Indio PD reviewed ten years of data and discovered that as truancy arrests shifted geographically in the city, burglaries appeared to follow one or two years later. As the sociologist dug deeper into the data, he identified individual students to whom school officials had mailed more than 100 letters about their absences.

“We assumed there was a correlation between daytime burglaries and truancy,” Police Chief Twiss said. “When you actually have the data that shows it, then you can evaluate the processes and the breakdowns in the processes.”

The police department launched several outreach programmes as a result, including a burglary and truancy prevention taskforce, community safety fairs and meetings, media campaigns and stronger partnership efforts with local business owners and others.

Confirmation of the truancy/burglary connection prompted the department to train staff to teach ‘Parent Project’ classes. The national programme is designed for parents raising difficult or out-of-control adolescents.

Police Chief Twiss said that although it is too soon to measure the impact of the programme, which Indio PD began in October, anecdotal reports are promising.

For example, a single mother whose son was habitually truant had attended only three parenting classes when she asked for help. A school resource officer met with her son in their home the next day to determine the reason for his absences and counseled him about the direction his life could take if he did not stay in school.

“That day he asked his mum to take him to re-enroll in school,” Police Chief Twiss said. “That’s a direct result of this programme. She felt comfortable that we weren’t going to have an arrest-and-book mentality.”

Police Chief Twiss said police do enforce daytime curfew violations and he also hopes to revive a youth court programme where trained teens would hear these cases.

“We are deploying people differently and doing more community outreach,” he said of the impact of the collaboration with Dr Parker. “We discuss in briefing those areas that are being impacted. We had our crime analyst put maps together a few mon