AAAI Publications, 2010 AAAI Spring Symposium Series

Font Size: 
Quantifying Behavioral Data Sets of Criminal Activity
Jameson L. Toole, Nathan Eagle, Joshua B. Plotkin

Last modified: 2010-03-16


With the increased availability of rich behavioral data sets, we present a novel combination of tools to analyze to analyze this information.  Using criminal offense records as an example, we employ cross-correlation measures, eigenvalue spectrum analysis, and results from random matrix theory to identify spatiotemporal patterns.  Finally, with multivariate autoregressive models, we demonstrate a possible source of structure within the data.


computational social science; correlation; crime

Full Text: PDF