An Alogrithm That Can Fight Crime

According to a study published in the journal Computational Statistics and Data Analysis, a recent algorithm created by the University of Surrey and Georgia Tech may hold the potential to predict reoccurring illegal activity. This algorithm, which will hold the ability to process data quickly, will give police departments a higher edge in their fight against crime. Across the world, police departments face an increasing pressure on their resources that is inducing the growth of policing software and other programs that will assist officials in making the best decisions. One such popular method is a program known as Epidemic Type Aftershock Sequence (ETAS). ETAS is a model (grid-map-based approach) consisting of urban crime data that will work urban crime data that works to predict two times as much crime as a single crime analyst.

In the study, investigators from Surrey and Georgia designed a detailed a novel approach quite similar to the approach examined in weather forecasting and the Apollo space missions. The new program, now called Ensemble Poisson Kalman Filter (EnPKF) will supplement ETAS to maximize the best resources in fighting crime. EnPKF is a new algorithm that will hold the ability to combine, in real-time, urban crime data as well as the ETAS model. It will work to provide real-time forecasts for the rate of crime giving an indication of the probability of a crime repeating again in a specific area. EnPKF will also hold the ability to “advise” police departments on where to head next for short-term crime hotspots and the resources they may require.

Additionally, if successful, researchers believe that EnPKF can also hold the ability to make forecasts by utilizing models other than ETAS such as monitoring train delays, earthquake aftershocks, and even insurance claims in sub-Saharan Africa. "We are cautiously excited about the Ensemble Poisson Kalman Filter, an approach that has given us an insight into when the crime can be predicted and has shown us the importance of using real-time data to make the overall system stronger. We are already well on our way to strengthening the algorithm and have even tested it against data from Chicago,” states Dr. David Lloyd from the University of Surrey's Department of Mathematics. “It is important to remember that EnPKF, and algorithms similar to this, are tools used to help our law enforcement who work hard to keep our communities safe. Their use will ultimately be determined by the needs of individual departments.”

Source: Science Daily