Part 4 BEHS Presentation Project

Running head: TECHNOLOGY AND CRIMINOLOGY 1

TECHNOLOGY AND CRIMINOLOGY 2

Machine Learning for Criminology

Quentin Tankersley

University of Maryland University College

November 13, 2018

Machine Learning for Criminology

In this presentation, I will be examining the impact of predictive analysis on criminology. Data mining has become an integral part of crime detection and processing. Through the use of machine learning and other predictive algorithms, security personnel have been able to analyze criminal data more effectively (Saeed, Sarim, Usmani, Mukhtar, Shaikh, and Raffat, 2015). Traditionally, such data was being analyzed manually by monitoring the behavior of individuals or groups that committed a crime (Rudin and Wagstaff, 2014). This approach was slow and tiresome, and not as much effective. Unlike humans, machines have higher computing powers and can easily identify criminals if they are fed with the right data. machines are also immune to the biases of race and social status exhibited in law enforcement agencies.

Predictive analysis begins by data mining where raw data is collected to create a database of information. This could be done by observing criminal trends of an individual such as the days and time they commit a crime, the tools used, and the contacts made (Wang, Rudin, Wagner, and Sevieri, 2013). The processes of inference and analysis are then applied to make predictions that can be applied to the real world. Big data analytics, artificial intelligence and the emerging internet of things play a big role in making this a reality.

My presentation topic has been informed by the high risks that the public and security personnel are exposed to when dealing with criminals. Predictive learning helps prevent crimes before they happen and makes it possible to make pre-trial detentions (Wang, Liu, and Eck, 2008). This technology also makes it possible to segregate high-risk offenders from less-harmful ones hence preventing possible injuries and deaths. Machine learning also makes it possible for social workers to counsel high-risk individuals since based on predicting their behaviors.

References

Lawrence, M., & Natarajan, M. (2015). Using Machine Learning Algorithms to Analyze Crime Data. Machine Learning and Applications: An International Journal (MLAIJ) Vol, 2.

Rudin, C., & Wagstaff, K. L. (2014). Machine learning for science and society.

Saeed, U., Sarim, M., Usmani, A., Mukhtar, A., Shaikh, A., & Raffat, S. (2015). Application of machine learning algorithms in crime classification and classification rule mining. Research Journal of Recent Sciences, 4(3), 106-114.

Wang, T., Rudin, C., Wagner, D., & Sevieri, R. (2013, January). Detecting Patterns of Crime with Series Finder. In AAAI (Late-Breaking Developments).

Wang, X., Liu, L., & Eck, J. (2008). Crime simulation using GIS and artificial intelligent agents. In Artificial crime analysis systems: Using computer simulations and geographic information systems (pp. 209-225). IGI Global.