Algorithm predicts crime by tracking mobile phones
For many years, scientists have been experimenting with algorithms capable of predicting crime. It is assumed that criminals tend to repeat successful actions - at least they do not use the RNG to select the place and time of the crimes, so their actions are predictable by definition.
For example, a year ago, the Californian city of Santa Cruz was the first in the world to introduce a mathematical model for calculating the probability of crime , which every day constitutes a new route for patrol cars, based on the statistics of crime on the streets. The day of the week, the time of day, the presence / absence of football matches on TV and other factors are taken into account.
Mirco Musolesi (Mirco Musolesi), a researcher at the University of Birmingham, took a completely different approach . His method is not based on statistics, but on operational data from cellular networks. Mousolezi began by teaching the algorithm, with a high degree of probability, to predict the movements of each subscriber: he even won the Nokia Mobile Data contest, most accurately predicting the movements of 25 volunteers from their phone signals, call history and text messages. Sometimes the algorithm predicts user coordinates with an accuracy of up to 20 m 2 .
The algorithm works effectively only if the entire network of friends of the specified user is monitored simultaneously. If you track only one person, the accuracy of the prediction of coordinates is reduced to 1000 m 2 . Even if it was possible to extract clarifying information from just one friend - the accuracy immediately increased dramatically.
')
Thus, the algorithm is able to calculate the place and time where in 20-30 minutes a group of potential criminals will meet. According to Mousolezi, it is possible to calculate a specific street, a quarter, sometimes even a house — the place of a potential crime. It is obvious that there just in case you need to send a patrol car.
Musolezi hopes that his development will be used by law enforcement agencies. The researcher is confident that such a data analysis system does not violate the law: “Our algorithm is a way to extract new information from the data [that the police already have],” he said in an interview with Forbes. Someone would call such a method dubious, because people are being monitored who have not yet committed crimes, but only for some criteria are included in the “risk group” (for example, citizens with a criminal background or mentioning a key word in a conversation on the phone or SMS). On the other hand, the algorithm itself works with anonymous data, so this “surveillance” is not fundamentally different from any contextual mobile advertising system or chat monitoring system for keywords that is used in Facebook and other services.
In principle, such algorithms can be used not only by the police, but also by ordinary commercial companies. Everyone will be pleased when you go to your favorite cafe - and there they just set the table for you. Or you come up to the house - and the kettle automatically turns on in the kitchen and dinner starts preparing.
Mirko Musolezi and colleagues published the results of their work (pdf), in the near future they are going to conduct additional experiments based on data provided by Nokia.
For example, a year ago, the Californian city of Santa Cruz was the first in the world to introduce a mathematical model for calculating the probability of crime , which every day constitutes a new route for patrol cars, based on the statistics of crime on the streets. The day of the week, the time of day, the presence / absence of football matches on TV and other factors are taken into account.
Mirco Musolesi (Mirco Musolesi), a researcher at the University of Birmingham, took a completely different approach . His method is not based on statistics, but on operational data from cellular networks. Mousolezi began by teaching the algorithm, with a high degree of probability, to predict the movements of each subscriber: he even won the Nokia Mobile Data contest, most accurately predicting the movements of 25 volunteers from their phone signals, call history and text messages. Sometimes the algorithm predicts user coordinates with an accuracy of up to 20 m 2 .
The algorithm works effectively only if the entire network of friends of the specified user is monitored simultaneously. If you track only one person, the accuracy of the prediction of coordinates is reduced to 1000 m 2 . Even if it was possible to extract clarifying information from just one friend - the accuracy immediately increased dramatically.
')
Thus, the algorithm is able to calculate the place and time where in 20-30 minutes a group of potential criminals will meet. According to Mousolezi, it is possible to calculate a specific street, a quarter, sometimes even a house — the place of a potential crime. It is obvious that there just in case you need to send a patrol car.
Musolezi hopes that his development will be used by law enforcement agencies. The researcher is confident that such a data analysis system does not violate the law: “Our algorithm is a way to extract new information from the data [that the police already have],” he said in an interview with Forbes. Someone would call such a method dubious, because people are being monitored who have not yet committed crimes, but only for some criteria are included in the “risk group” (for example, citizens with a criminal background or mentioning a key word in a conversation on the phone or SMS). On the other hand, the algorithm itself works with anonymous data, so this “surveillance” is not fundamentally different from any contextual mobile advertising system or chat monitoring system for keywords that is used in Facebook and other services.
In principle, such algorithms can be used not only by the police, but also by ordinary commercial companies. Everyone will be pleased when you go to your favorite cafe - and there they just set the table for you. Or you come up to the house - and the kettle automatically turns on in the kitchen and dinner starts preparing.
Mirko Musolezi and colleagues published the results of their work (pdf), in the near future they are going to conduct additional experiments based on data provided by Nokia.
Source: https://habr.com/ru/post/149184/
All Articles