Predictive Policing Blog

SacBee Online - PredPol Results in "Dramatic Crime Reduction"

Posted on Oct 16, 2013 9:19:27 AM in LAPD, Predictive Policing, PredPol, UCLA

Cities that have implemented PredPol, a computer software program that predicts when and where crime will occur, have seen "cliff-like" drops in crime often within months of deployment. PredPol is a secure, cloud-based software-as-a-service, developed by a team of PhD mathematicians, criminologists, and social scientists at UCLA, Santa Clara University, and UC Irvine in close collaboration with crime analysts and line level officers at the Los Angeles and Santa Cruz Police Departments. In just six months after launch, those first two cities saw crime reductions of 12% to 25% in burglaries and auto thefts compared to the previous

Since that time, targeted crimes have continued to drop in Los Angeles, Santa Cruz and in numerous other agencies that have deployed the technology. "I'm convinced that predictive policing works," LAPD Captain Sean Malinowski told NBC Southern California. A study of crime data going back 80 months shows a "cliff-like drop" when predictive policing began, according to Captain Malinowski.

After these successful initial deployments PredPol has deployed its groundbreaking technology in dozens of cities around the United States as well as the United Kingdom. In Alhambra, California, police are using PredPol to target three primary crime types: car theft, theft from vehicles and auto burglary. Since deployment, those crimes have gone down by 7 percent, 20 percent and 32 percent respectively. "PredPol is an invaluable added tool that allows our police force to use their patrol time more efficiently and helps stop crime before it happens," Alhambra Chief Mark Yokoyama told the Global Times. "This technology offers an excellent crime-fighting solution that will ultimately make Alhambra safer."

PredPol's core technology has grown from success with property crimes to include prediction of drug crime, gang crime, anti-social behavior, and the recently released gun violence prediction tool. Kent Police in England have watched as violent crime has dropped by 6 percent since they began using PredPol's tool and now the Seattle Police Department have partnered with PredPol to predict and deter gun violence.

Dr. George Mohler, PredPol co-founder and professor of mathematics and computer science atSanta Clara University noted that, "while no single strategy can end gun violence, predictive policing gives officers a significantly better idea of when and where to be so that they can deter crime. If we can prevent just one gun crime, that will mean one less neighbor, friend, or family member who becomes a victim."

PredPol's unique crime prediction methodology leverages existing crime data that every city already has, advanced mathematics developed over more than six years, computer learning, cloud computing, and the indispensable experience of veteran police.  The crime data is analyzed through a sophisticated algorithm that applies proven criminal theories about crime – including gun violence.  The results are more accurate and more actionable recommendations for when and where crime is most likely to occur, thus allowing police to show up before crime happens.

PredPol has extensively modeled this new approach to deterring gun violence, predicting a greater number of gun homicides compared with existing approaches, including traditional hotspot maps. PredPol successfully outperforms current best practices by 66 percent.

This corresponds with even stronger performance that police agencies have seen with PredPol's broader technology for predicting and preventing other violent crimes and property offenses.  In scientifically controlled experiments in Los Angeles and Kent, England, PredPol's predictions not only reduced crime but were 100 percent more accurate than existing best practices – predicting double the number of crimes as current crime mapping and hotspot analysis.

Without predictive analytics, police are forced to chase yesterday's crime by relying on simple mapping of past crime data. It would be like forecasting the weather using only historical weather patterns, but ignoring weather radar.  Traditional crime mapping tools are calibrated less frequently, rely more on humans to recognize patterns, and allocate resources based on past crimes rather than predicted future offenses. PredPol does not replace the insights of veteran officers and crime analysts, but delivers an easy-to-use enhancement that lets police do more with their current resources.

Read more here: http://www.sacbee.com/2013/10/15/5822418/predpols-innovative-predictive.html#storylink=cpy