It isn’t often that managers can look to law enforcement for clues on how to more effectively do their work. After all, how many people with a business degree ever took a class called “Catching Bad Guys”? But police are delivering an important lesson on the use of GIS by utilizing geospatial predictive analysis to find meth labs before criminals establish them.
Researchers Max Lu and Jessica Burnum have described how methamphetamine labs in the city of Colorado Springs between 2002 and 2005 didn’t pop up in a random distribution. Rather, their positions are clustered “in neighborhoods with a young and predominantly white population, small household size, and low education levels.”
What the researchers did was correlate socioeconomic data with the locations of seized labs and sites of toxic byproducts of the chemical processes that create meth. They used basic geospatial predictive modeling theory: Things don’t happen in random patterns in the world. Instead, various environmental factors come into place. They may be socioeconomic, like the data Lu and Burnum used. They could also represent other factors, such as geography or various elements of infrastructure.
Law enforcement use of geospatial analytics has moved far beyond a couple of researchers or the fictional exploits of the television show Numb3rs. A growing number of police departments around the country find that they can use the techniques to identify “discernable geospatial preferences associated with a perpetrator’s conscious and unconscious activities leading up to criminal behavior, a gang action, or a terrorist threat.”
It’s statistical prediction of the future based on associating relevant factors–sometimes thousands of types of measurement–with geography. Experts sift through past crimes and the characteristics of the places they occurred. The result isn’t a giant arrow pointing to the guilty party. Rather, geospatial predictive analysis gives other locations where similar crimes might likely take place.
Moving from crime fighting to business is a short step, because the fundamental concepts are the same. Instead of crimes and the people that commit them, a company looks for things relevant to its strategy: customers, neighborhoods where marketing campaigns were particularly effective, areas that a competitor is relatively strong, locations for new retail outlets, parts of a supply chain that have problems that could disrupt the flow of goods.
Companies can use the techniques to identify situations that aren’t directly related to their businesses, but that could adversely affect them. It takes little wondering to see how predicting areas that see terrorist activity, political instability, labor strikes, transportation disruptions, and the like can help a company plan for potential disruptions.
Geospatial predictive analysis is just another reason why managers should advance their knowledge of GIS. Failing to do so might give a critical advantage to competitors who adopt it.