Google maps finds the closest Starbucks and Meth Labs

Researchers are now using google maps in concert with a technique called "Geospatial Predictive Analysis" to predict and police illegal activities ranging from meth labs to burglaries:

Max Lu, a professor at Kansas State University, developed a novel method of finding meth labs through geospatial predictive analytics. In the 2009 book Geography and Drug Addiction, Lu and partner Jessica Burnum applied spatial data analysis tools to compiled information on the informal meth industry in Colorado Springs and rural Kansas. Burnum and Lu examined data collected from 2002 to 2005 on seized meth lab equipment and where rogue chemists dumped the toxic by-products of methamphetamine manufacture. Using the data, the pair were able to successfully prove meth manufacture was creeping slowly through more and more middle-class neighborhoods in Colorado Springs. Map data analyzed over time successfully demonstrated the spread of meth labs throughout a metropolitan area--and even predicted where they would pop up next.

The key word here is "predicted." It's impressive to have a model that matches your data after the fact. It's an entirely different thing to use a model that can predict and possibly intercept crime. That is just awesome. With any luck they may even find Heisenberg.

Ed

Ed enjoys all forms of entertainment and has an unnatural love for quantitative methodology. He operates out of a basement in Northern Virginia (@edomaniac).

---

This post originally appeared on Stuff Smart People Like. Subscribe to the Podcast.