An AI algorithm has been developed that predicts crimes a week ahead

(ORDO NEWS) — An algorithm with an accuracy of up to 300 meters allows you to predict where an attack or theft will take place a week before it happens.

While such predictive models can enhance the power of the state through the illegal surveillance of innocent people, at the same time they allow surveillance of the state by revealing systemic bias in the actions of law enforcement agencies.

Advances in machine learning and artificial intelligence have generated considerable interest from governments around the world.

And their interest is understandable: if there were a working tool for predicting crimes, this would greatly simplify the work of law enforcement agencies and, in the future, drastically reduce the level of street crime.

One such model, which gives weekly predictions of terrorist attacks based on data only from open sources.

However, most previous attempts at predicting crime have been rather inconsistent and inaccurate. Mainly because they often used the so-called epidemic or seismic approach, when crime occurs in certain “hot spots”, which then spread to nearby areas.

At the same time, the complex social environment of cities and their natural topology are overlooked, the relationship between crime and the consequences of police coercion is not taken into account.

Data analysts and sociologists from the University of Chicago (USA) have developed a new algorithm that predicts crime by studying patterns in time and geographical distribution of violent crime (murder, assault, battery, and so on) and crimes against property (burglary, general street theft and car theft, etc.), using only publicly available data.

The model can predict future crimes for the week ahead with an accuracy of about 90%. Scientists described their stochastic inference algorithm.

The new model divides the city into identical squares with a side of about 300 meters, analyzes the time and place of individual crimes and identifies patterns to predict future events. Initially, the model was tested on data on attacks and thefts in the third most populated city in the United States of America – Chicago.

However, the model worked just as well with data from seven other US cities: Atlanta, Austin, Detroit, Los Angeles, Philadelphia, Portland, and San Francisco.

As part of a separate predictive model, the research team examined police responses and responses to crime in different parts of the city by analyzing the number of arrests after relevant incidents and comparing these rates among areas of different socioeconomic status.

The authors of the paper noticed that higher crime rates in richer areas lead to more arrests in them, while the number of arrests in disadvantaged areas decreases.

However, a similar increase in crime in poor areas does not lead to the expected increase in arrests there, indicating a bias in police response and enforcement.

And yet, despite the high accuracy of its crime prediction model, scientists note that it should not be used directly for law enforcement.

After all, an increase in the number of police officers in those areas of the city where a crime is expected will lead to a change in the conditions of modeling and will only reduce the efficiency and accuracy of prediction. Instead, the model should be added to the toolbox of urban policy and police strategies to combat crime.

“We have created a digital twin of the urban environment. If you give him data about what happened in the past, he will tell you what will happen in the future. It’s not magic, there are limitations, but we tested the model and it works very well.

Now you can use it as a simulation tool to see what happens if crime rises in one area of ​​the city or law enforcement increases in another area.

If you use all of these variables, you can see how systems evolve in response,” summed up Ishanu Chattopadhyay , assistant professor of medicine at the University of Chicago and senior author of the new study.


Contact us: [email protected]

Our Standards, Terms of Use: Standard Terms And Conditions.