Making Use of Big Data to Evaluate the Effectiveness of Selective Law Enforcement in Reducing Crashes

Abstract

State departments of transportation across the nation fund selective enforcement campaigns aimed at intensifying law enforcement at certain locations to improve traffic safety. At the same time, many states passively collect large data sets, such as officer GPS location tracks. To evaluate the effectiveness of selective enforcement, an approach was developed to employ structured query language (SQL) and geographic information system (GIS) technology to mine and integrate police patrol patterns, citations issued, crash occurrences, and selective enforcement periods. This information was analyzed in a relational database within a spatial and temporal analysis framework. The intent was to use solely GIS technology; however, the size of the data sets was prohibitive, and SQL was used as a big data analytic. The SQL techniques successfully turned more than 37 million points of GPS data into 1.3 million points of selective enforcement location information, enabled the geolocation of 72.6% of electronic citations, and identified 21 selective enforcement areas across the state of Alabama. With big data analytics, GIS technology was reestablished as useful for the evaluation of changes in crash and citation frequencies before and during selective enforcement. Paired difference t-tests confirmed the decrease of crash frequency with 85% confidence at urban and rural locations. The analysis of the number of citations at the locations confirmed that citations increased during selective enforcement by an average of 254%. The developed methodology is a successful approach using large data sets for an unintended purpose to make valuable engineering conclusions and data-driven discoveries.