Crime Data Mining

TL;DR: This work looks at use of clustering algorithm for a data mining approach to help detect the crimes patterns and speed up the process of solving crime, and develops a weighting scheme for attributes to deal with limitations of various out of the box clustering tools and techniques.

Abstract: Solving crimes is a complex task and requires a lot of experience. Data mining can be used to model crime detection problems. The idea here is to try to capture years of human experience into computer models via data mining. Crimes are a social nuisance and cost our society dearly in several ways. Any research that can help in solving crimes faster will pay for itself. According to Los Angeles Police Department, about 10% of the criminals commit about 50% of the crimes. Here we look at use of clustering algorithm for a data mining approach to help detect the crimes patterns and speed up the process of solving crime. We will look at k-means clustering with some enhancements to aid in the process of identification of crime patterns. We applied these techniques to real crime data from a sheriff’s office and validated our results. We also used semi-supervised learning technique here for knowledge discovery from the crime records and to help increase the predictive accuracy. Our major contribution is the development of a weighting scheme for attributes, to deal with limitations of various out of the box clustering tools and techniques. This easy to implement data mining framework works with the geo-spatial plot of crime and helps to improve the productivity of the detectives and other law enforcement officers. It can also be applied for counter terrorism for homeland security.