Citizen security using machine learning algorithms through open data

Abstract

The following work is an application proposal based on machine learning algorithms for a possible solution for the public safety problem in a South American city. The aim of this application is to reduce the threat risk of the physical integrity of pedestrians by geolocating, in real-time, safer places to walk. In this context for a city, San Isidro, a business district of Lima, has been established as study case. The district has been divided into map sectors and subsectors, so that by using the GPS location service integrated in mobile devices, it is possible to identify areas that have the highest incidence of different types of incidents. This functionality will allow users to choose safer routes by taking into account the information provided for each sector. The data used in this application has been obtained from an Open Data platform managed by the San Isidro municipality. In this application, we have processed the data enabling the easy and friendly access to the information by the end user. The importance of this work is how we have used the machine learning algorithm for incident rates in real and future time, trying to make predictions that can not only provide safe routes to users, but also predict disasters and allow public authorities to act in advance, thus minimizing the impact of future incidents.