Predicting the spread of crime incidents

Discussion created by daviddesmond on Dec 10, 2013
Hello, I'm hoping someone can help me figure out how to approach a problem. I'm pretty sure that I'm over-thinking it.

I have a table of crime incidents that contains the date and address that each crime took place. The table can be easily geocoded. It is my hope that I can use the location and date of past crimes to predict the location of future crimes. In my mind the result of the project will be a series of past crime heat maps (by year) along with some type of predictive crime heat map.

I'm open to suggestions, if anybody can get me pointed in the right direction I would greatly appreciate it.