Abstract
Korean police agencies can discover useful trends and patterns using machine learning algorithms. However, which algorithm to select is difficult problem, because the accuracy and performance of machine learning algorithms may depend on dataset used for analysis and purpose of analysis itself. In this short paper, we describe a study on performance evaluation of machine learning algorithms for crime dataset. Unlike previous methods, we employ the real South Korean crime dataset that we collected from various sources, and carry out performance evaluation of well-known machine learning algorithms on this real crime dataset. As far as we know, this is the first attempt on performing such kind of research using South Korean crime dataset.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
