A Business Intelligence System to Support Crime Management in Law Enforcement Agencies: a Case of Uganda Police Force

Abstract

Police data is continuing to grow at a high rate and it will be doubling every two years; police uses only 17% of its crime data in crime management today (Xerox, 2013). Nicole’s study of 2012 concluded that Law Enforcement Agencies are data rich but information poor and Uganda Police Force (UPF) is not an exceptional. Jacob et al. (2015) revealed Uganda Police Crime Case Management System support police officers in the management of crime cases, storage and retrieval of complainants’ and offenders’ information as well as to follow up the case status and keep track of information concerning crime cases in the Uganda Police Force. Also (Oludele et al. 2015) revealed that A Real-Time Crime Records Management System for National Security Agencies is an efficient and effective data analysis tool for improving the operations of the law enforcement agencies. Anil et al. (2013) argued that Crime Automation and Reporting System would allow the reporting of crimes 24/7 by the victims and witnesses. Jimoh et al. (2014) argued that a scalable Online Crime Reporting System would help the police to timely get the information about criminals and their mode of operation and also allows crime reporting with anonymity. Developing a low cost Business Intelligence system for crime data analytics requires low cost development tools and this is where open source business intelligence tools come to a play. Therefore there was a need to identify an efficient and effective open source business intelligence tool for the implementation of a Business Intelligence System for crime data analytics. Five Open Source BI tools i.e. Apache Hadoop, Jaspersoft, Pentaho, SpagoBI and vanilla were considered. Apache Hadoop is recommended by this research for crime data analytics because it has capabilities which are not found to other open source tools. Also a BI system was developed using Hadoop ecosystem, the system allows structured, semi structured and unstructured data, audios and videos for crime data analytics. Also the system is fault tolerant, easy to use and is economically feasible and it will therefore act as a reference point by the law enforcement agencies during the implementation of BI and Crime analytics systems. Also four different classification algorithms that is; decision tree (J48), Naïve Bayes, Multilayer Perceptron and Support Vector Machine were compared to find the most effective algorithm for crime prediction. The study used classification models generated using Waikato Environment for Knowledge Analysis (WEKA). The study revealed that the average accuracy of J48, Naïve bayes, Multilayer Perceptron and Support Vector Machine (SMO) is approximately 100%, 89.7989%, 100% and 92.6724%, respectively for both training and test data. Also the execution time in seconds of J48, Naïve bayes, Multilayer Perceptron and SVO is 0.06, 0.14, 9.26 and 0.66 respectively using windows7 32 bit. Hence, Decision Tree (J48) out performed Naïve bayes, Multilayer Perceptron and Support Vector Machine (SMO) algorithms, and manifested higher performance though J48 had little execution time as compared to Multilayer Perceptron. The researcher recommends that this project would further be developed by incorporating real-time Business Intelligence. This implies that, Hadoop should be connected to the information systems and also social media to stream live content and update dashboards in near real-time.