Crime detection and criminal identification in India using data mining techniques

In the current paper, we propose an approach for the design and implementation of crime detection and criminal identification for Indian cities using data mining techniques. Our approach is divided into six modules, namely—data extraction (DE), data preprocessing (DP), clustering, Google map representation, classification and WEKA^® implementation. First module, DE extracts the unstructured crime dataset from various crime Web sources, during the period of 2000–2012. Second module, DP cleans, integrates and reduces the extracted crime data into structured 5,038 crime instances. We represent these instances using 35 predefined crime attributes. Safeguard measures are taken for the crime database accessibility. Rest four modules are useful for crime detection, criminal identification and prediction, and crime verification, respectively. Crime detection is analyzed using k-means clustering, which iteratively generates two crime clusters that are based on similar crime attributes. Google map improves visualization to k-means. Criminal identification and prediction is analyzed using KNN classification. Crime verification of our results is done using WEKA^®. WEKA^® verifies an accuracy of 93.62 and 93.99 % in the formation of two crime clusters using selected crime attributes. Our approach contributes in the betterment of the society by helping the investigating agencies in crime detection and criminals’ identification, and thus reducing the crime rates.