The Woodland Police Department has launched a new computer program that uses local crime data to anticipate and reduce criminal activity.
PredPol, or Predictive Policing, is described as Internet-based software that uses an algorithm to assist officers in deciding where their patrols would be most effective, according to a Police Department news release. Using an earthquake aftershock algorithm, the system employs verified crime data to predict future offenses in 500-square-foot locations. The program uses historical information and current data to determine patterns.
No personal information is used in the program, officials said, only the type, place and time of the crime.
Officers receive predictions for 500-square-foot geographic "boxes" on Google maps that forecast when and where crime is most likely to occur, officials said. Officers then spend extra time in those areas during their shifts when they aren't responding to calls for service or performing other duties.
Predictive Policing was developed when the Los Angeles and Santa Cruz police departments in 2005 asked a group of PhDs about using technology and high-level math to help police deal with crime in the face of limited staffing and budgets. In Santa Cruz, with a population of 60,000, the the program is credited with helping reduce the number of burglaries by 19 percent, according to the news release. In the first Los Angeles police division where it was employed, property crimes were cut by 12 percent. Statistics in both cases are for the first six months after deployment in fall 2011.
Other cities that also have decided to use the technology include Seattle, San Francisco and Atlanta.