Empirical Analysis on Crime Prediction using Machine Learning

Criminal offence or Crime is an detrimental act that not only affects an individuals but affects an community. In the current scenario crimes sequences happens every second in various places, in various crime patterns, as the results the crime rate is increasing each growing places. It is very much essential to determine the different factors for the possible occurrence of crimes and find the optimized ways to reduce the crime. Crimes can be compartmented into multiple factors like Rape, Murder, Assault and Theft and so on. Data were gathered from National Crime Records Bureau. This proposed work focuses to apply various machine learning algorithms such as Naïve bayes, Random forest, Decision tree and Support vector machine and Logistic regression for reducing of crime rates in India. Performance of the proposed models compared with various measures like precision, recall, accuracy, and fl score along with the confusing matrix. Also considers the error value for various models with the help of mean absolute error technique. As a result, the Naïve bayes model gives the best results of 98.94% comparing with other.

I. Introduction

One of the challenging and dominating the task in our society is preventing crime. It is very much essential to find the different mechanisms to identify the factors of crime as well as to reduce them in right way at right place. Crime prediction and criminal identification are the important critical issues to the Department of police as there are tremendous amount of crime data that exists. A crime happens on a vast count, in different patterns and the number of crime incidents growing each day. Past existing data is used for crime analysis.