Crime pattern detection, analysis & prediction

Crimes are a social irritation and cost our society deeply in several ways. Any research that can help in solving crimes quickly will pay for itself. About 10% of the criminals commit about 50% of the crimes [9]. The system is trained by feeding previous years record of crimes taken from legitimate online portal of India listing various crimes such as murder, kidnapping and abduction, dacoits, robbery, burglary, rape and other such crimes. As per data of Indian statistics, which gives data of various crime of past 14 years (2001–2014) a regression model is created and the crime rate for the following years in various states can be predicted [8]. We have used supervised, semi-supervised and unsupervised learning technique [4] on the crime records for knowledge discovery and to help in increasing the predictive accuracy of the crime. This work will be helpful to the local police stations in crime suppression.

[1]  Shyam Varan Nath,et al.  Crime Pattern Detection Using Data Mining , 2006, 2006 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology Workshops.

[2]  Victor Maojo,et al.  A Survey of Data Mining Techniques , 2000, ISMDA.

[3]  Mugdha Sharma Z - CRIME: A data mining tool for the detection of suspicious criminal activities based on decision tree , 2014, 2014 International Conference on Data Mining and Intelligent Computing (ICDMIC).

[4]  Raju K. Gopal,et al.  Data mining based crime investigation systems: Taxonomy and relevance , 2015, 2015 Global Conference on Communication Technologies (GCCT).