In order to improve police efficiency and reduce costs, the Igarapé Institute is developing CrimeRadar, a user-friendly, real-time hotspot mapping and crime forecasting platform for law enforcement. At the center of the solution is an algorithm that processes current and historical data from emergency hotlines and police reports, generating crime hotspot maps. The solution deploys regression models and supervised machine learning techniques to determine the probability of a crime event occurring at specific times of day and days of the week in 500×500 meter quadrants of a city.


Prior to the 2016 Rio Olympics, the Igarapé Institute developed rio.CrimeRadar, a digital platform that used machine learning to predict crime rates in different neighborhoods at different times. The platform was soft launched to the public during the Rio Olympics, in August of that year, and focused on the city’s metropolitan area. CrimeRadar drew on over five years of crime data collected by the Rio de Janeiro state police to determine relative crime risks for the upcoming week. The app was conceived and developed by Igarapé Institute, associated with Via Science and Mosaico.

Notice – the algorithm and data are currently not being updated, and forecasts will tend to lose relevance over time.

Why use CrimeRadar?

Research shows that violent crime and property crime are not only highly concentrated in specific locations (or ‘hotspots’), but also tend to occur at predictable intervals. There is strong evidence that if crime can be prevented at those hotspots, then total crime in the city can also be reduced.

CrimeRadar can integrate existing GPS location data of officers provided by the department. From a dashboard, commanders can visualize real-time maps with the positions of officers and the locations where the probability of crime is highest. Alternatively, where GPS data is not available, an accompanying smartphone application can be provided to track the location of officers. The solution can be used as an affordable option to track the locations of patrol cars, fire cars, and ambulances.

By increasing situational awareness, CrimeRadar can improve Police resource allocation, contributing to:

  1. Reduced average response times
  2. Reduced fatalities and crime incidents
  3. Department’s improved trust, legitimacy and authority

Developing the CrimeRadar Police-Facing Tool

The Igarapé Institute has formalized a collaboration with the Military Police of Santa Catarina, Brazil, and with researchers from the University of Warwick, UK, to develop and pilot a police-facing CrimeRadar tool to assist in the planning of operations, aiming to optimize the allocation of policing resources.

CrimeRadar pilots are ongoing in 2019 in selected cities in Santa Catarina. A Randomized Controlled Trial (RCT) will be implemented in 2020 to assess the effectiveness of CrimeRadar in the planning of police patrol itineraries and scheduled operations. Changes in crime levels, average police response times, and public trust in the police will be assessed. The study results will be published in academic journals, and showcased on a roundtable with specialists in criminology, civil rights, digital rights, and other related fields.

What is more, the Institute has secured resources to replicate the CrimeRadar initiative in South Africa, starting in 2019. The project will involve two phases: (i) developing and piloting the app with a Metropolitan Police and (ii) scaling up the initiative with up to five pilots in Brazil, South Africa, and other locations.

Built-in Transparency and Licensing

CrimeRadar will be made available to other police departments upon request. To use the tool, departments must comply with minimum transparency and reporting standards. The Institute will support the departments to make sure that the standards are met.

The requirements are laid out below, along with the Primary Accountable Institution (PAI). These requirements follow the recommendations from the FAT/ML work group:

    • Responsibility and Recourse – Make available externally visible avenues of redress for adverse individual or societal effects of an algorithmic prediction system, and designate an internal role for the person who is responsible for the timely remedy of such issues. (PAI: Police Department)
    • Explainability – Ensure that algorithmic predictions as well as any data driving those predictions can be explained to end-users and other stakeholders in non-technical terms. (PAI: Police Department)
    • Accuracy – Identify, log, and articulate sources of error and uncertainty throughout the data sources so that expected and worst case implications can be understood and inform mitigation procedures. (PAI: Police Department)
    • Fairness – Ensure that algorithmic predictions do not create discriminatory or unjust impacts when comparing across different demographics. (PAI: Police Department)
    • Auditability – Enable interested third parties to probe, understand, and review the behavior of the algorithm through disclosure of information that enables monitoring, checking, or criticism, including through provision of detailed documentation, technically suitable APIs, and permissive terms of use. (PAI: Igarapé Institute).

Featured by