Hitachi Develops Crime Predicting Tech For Police Testing
Society just got a little bit closer to making the Minority Report a reality.
Hitachi has developed a technology dubbed the Visualization Predictive Crime Analytics (PCA) to anticipate crimes before they are committed, Sean Captain of Fast Company reports.
The system is based on machine learning, a technique of recognizing patterns or outliers from enormous data sets. The job of the Hitachi PCA will be to sift through the data that plays a role in affecting crime.
Darrin Lipscomb and Mark Jules, are cofounders of the tech companies Avrio and Pantascene and two of the developers of the Hitachi PCA.
Lipscomb noted some of the variables that affect crime data like the “weather, social media, proximity to schools, Metro [subway] stations, gunshot sensors, 911 calls.” All that information is logged into the PCA, but that is by no means an exhaustive list.
One of the aims of the technology is to remove or limit the element of preconceived notions from law enforcement investigations. “We’re trying to provide tools for public safety so that [law enforcement is] armed with more information on who’s more likely to commit a crime…I can use data and intelligence and software to really augment what police are doing, ” Lipscomb told FastCompany.
“You just feed those data sets and it decides, over a couple of weeks, is there a correlation,” said Jules.
Social media plays a significant role in the system’s predictive modeling and the PCA has been programmed to understand slang or informal speech.
“Gangs, for instance, use these different keywords to maybe meet up or perform some action,” said Lipscomb. “I don’t know what that keyword is … but with our approach we can actually pick out something that’s abnormal, like someone’s using an off-topic word, and using it in a very tight density or proximity, and that’s going to get a bigger weight.”
Trial runs using the PCA are to begin in October in a number of cities.
Content created by The Daily Caller News Foundation is available without charge to any eligible news publisher that can provide a large audience. For licensing opportunities of our original content, please contact firstname.lastname@example.org.