In the era of “big data”, a huge number of people, devices, and sensors are connected via digital networks, and there is tremendous amount of data generated from their interactions every day. Effective processing and analysis of big data could reveal valuable knowledge that enable us to deal with emerging problems in a timely manner. However, rarely we can find big data analytics models and methods for crime forensics discussed in existing literature. In this paper, we illustrate a novel big data analytics framework that leverages heterogeneous big data resources for criminal pattern detection. The proposed framework can uncover the inherent structural properties of criminal networks which are essential for both crime investigation and the development of operational strategies to disrupt criminal networks. The structural analysis functionality generated by our proposed system could significantly improve the efficiency and accuracy of network analysis tasks. The proposed framework consists of two important analytical approaches, namely structure analysis, and network mapping. Based on the proposed framework, we have developed a prototype system called Automatic Crime Detector (ACD) that incorporates several big data analytic methods. Our empirical evaluation shows that the proposed framework is effective for criminal network discovery.
Pramanik, Md Ileas; Lau, Raymond Y.K.; and Chowdhury, Md Kamal Hossain, "Automatic Crime Detector: A Framework for Criminal Pattern Detection in Big Data Era" (2016). PACIS 2016 Proceedings. 311.