Data-driven decision support to reduce "driving-under the influence of alcohol" offenses

Abstract

Extracting valuable knowledge from data to support decision making is a widely practiced trend. Data-driven decision support (DDDS) provides insight for decision makers by exploring and extracting underlying patterns within a dataset. This thesis covers the process of DDDS in reducing driving under the influence of alcohol (DUI) offenses by introducing proposed prison sentences. In this thesis, DDDS is applied to a DUI dataset by analyzing patterns in the dataset and by introducing proposed prison sentences for offenders to reduce the number of DUI cases. Background theories in data mining, machine learning, optimization and decision science that are related to the thesis project are also covered. Furthermore, the thesis presents the application of data analysis and multiobjective optimization, in formulating and optimizing objective functions representing DUI reduction. The results obtained from the analysis show that, by grouping individuals with similar DUI patterns and by introducing different proposed prison sentences for each group, it is possible to provide decision support that can reduce the number of DUIs at certain time intervals.