Definition of public safety policies based on the characterization of criminal events using volunteered geographic information, case study: Mexico

For the study of the criminal incidence and the definition of security policies focused on reducing the crime rate in a specific geographic region, authorities based their policies on both the user crime reports obtained from governmental dependencies and the estimation of the unrecorded crime rate, which are formally defined as the percentage or number of offenses that it is not notified. Unfortunately, Mexico is one of the countries with the highest unrecorded crime rates worldwide. So, according to different unofficial reports, in 2016, the unrecorded crime rate for common jurisdiction crimes was greater than 90%. Thus, it is not possible to define an efficient decision-making process because the real number of crimes, specially the specific geographic location of these crimes, is not known. In 2016, the official INEGI reported two main factors that contribute with the unrecorded crime rate: corruption and lack of confidence (victim personal information) provided from government security institutions. In recent years, several web and mobile applications have been developed, based on volunteered geographic information scheme to collect criminal anonymous information related to this issue. However, the point to define methodologies that allow us to identify multiple records related to the same crime event is necessary. The main goal of this chapter is to generate public policies and guidelines to improve the administration of justice, taking into consideration certain values of criminal incidence, along with a clear identification of kinds of events presented. Thus, this chapter is oriented to generate statistical data by applying ITC technologies to produce both good and safety policies. In addition to this, a case study focused on the application of artificial intelligence algorithms to analyze and classify crime reports is presented as well.