- Joined
- Mar 3, 2018
- Messages
- 1,713
Researchers from RMIT University in Australia used data from social media platforms to predict crimes more accurately than existing models. The researchers used check-in data from Foursquare to generate a model of where potential victims will be, and then looked for areas where that routine intersects with known criminal activity. They say this data can be used to optimize police patrols dynamically, as opposed to using static, traditional models. The researchers also note that the results are remarkable, given the limited amount of data they used, and that there's more potential for prediction. The full research paper is available for free.
"Current state-of-the-art crime prediction models generally rely on relative static features including long-term historical information, geographical information and demographic information. This information changes slowly over time, meaning these traditional models couldn't capture the short-term variations in crime event occurrences," Rumi says. "Our test results demonstrate the improvement of prediction performance after adding dynamic features is considerable and statistically significant. That really is revolutionary." The group is now planning to extend the work by training the algorithms using data from one city and increasing its ability to apply those learnings in a different city where patterns are different.
"Current state-of-the-art crime prediction models generally rely on relative static features including long-term historical information, geographical information and demographic information. This information changes slowly over time, meaning these traditional models couldn't capture the short-term variations in crime event occurrences," Rumi says. "Our test results demonstrate the improvement of prediction performance after adding dynamic features is considerable and statistically significant. That really is revolutionary." The group is now planning to extend the work by training the algorithms using data from one city and increasing its ability to apply those learnings in a different city where patterns are different.