Gyeongseok Oh
Sam Houston State University, USA
Title: Crime Prediction Using Administrative Big Data and Machine Learning
Biography
Biography: Gyeongseok Oh
Abstract
It is indisputable that machine learning techniques and big data analysis have become the main topics in almost all discipline of science and industry during the past decade. Concurrently, numerous governments in the world are collecting enough amount of administrative data that can be analyzed by machine learning techniques to investigate the causes of social phenomena and to improve the efficiency of public administration. Despite the data analytic techniques and the capability of data storage have been remarkably improved, a large number of scholars in the field of social science hold conservative perspective on applying machine learning and big data analysis to explaining social phenomena. The goal of this study is to fill the void by providing empirical evidence. The present study will attempt to examine the validity of using administrative big data to predict crime incidents. Records of calls for service through 311 mayor’s hotline system in Houston, Texas and the official crime reports of Houston Police Department were examined to assess whether signs of physical decay and the presence of social nuisance predict the crime incidents at neighborhood level. The results of this study will corroborate the Broken Windows Theory and present new windows to explore the causes of crime. Several policy implications for government and police administrators will be developed and discussed.