Predicting Violent Crime Occurrence: An Evaluation of Decision Tree Model

Abstract

Crime rate tends to be on the increase across the globe, and crime data analysis becomes imperative to aid predictive policing in tackling incidence of crime. In this paper data mining approach was applied to violent crime dataset for predicting next occurrence of violent crime. Previous researchers have used different supervised learning algorithms for crime prediction with accuracy results left to be improved upon. Consequently, this study particularly apply decision tree C5.0 algorithm on violent crime dataset in order to determine the probability of next occurrence of violent crime in Lagos metropolis. The data used was derived from Nigerian Police statistic department Obalende Lagos, pre-processed and applied on decision tree model built. The model was evaluated using the six violent crime types (murder, arm robbery, kidnapping, rape, non-negligent assault and man slaughter) dataset. The results obtained were evaluated using confusion matric and found to return an accuracy of 76.4% (percent). Based on this result, the model could be used by the Police authority to strategize and plan towards mitigating crime rate in the country.

Education on Human Rights and Good Governance in Nigeria: A Case Study of Sars

“…Sadly, that is the case; numerous complaints and reports have been filed against numerous officers citing rape allegations; one such case was the police raid of April 29th, 2019, where over 65 women were arrested at a nightclub by Nigerian taskforce during a raid, according to several eye witnesses; the victims were Proceedings of ADVED 2022-8th International Conference on Advances in Education, Istanbul, Turkey 10-12 October 2022 selected at random, mostly women who wore "skimpy attire," and taken to Utako prison where they were charged with prostitution; beating, threatened, and threatened (Adesola, Azeta, Oni, Chidozie, & Azeta, 2020).…”