Once Upon a Crime: Towards Crime Prediction from Demographics and Mobile Data

Rucking_Fetard

http://arxiv.org/abs/1409.2983

In this paper, we present a novel approach to predict crime in a geographic space from multiple data sources, in particular mobile phone and demographic data. The main contribution of the proposed approach lies in using aggregated and anonymized human behavioral data derived from mobile network activity to tackle the crime prediction problem.

While previous research efforts have used either background historical knowledge or offenders' profiling, our findings support the hypothesis that aggregated human behavioral data captured from the mobile network infrastructure, in combination with basic demographic information, can be used to predict crime. In our experimental results with real crime data from London we obtain an accuracy of almost 70% when predicting whether a specific area in the city will be a crime hotspot or not. Moreover, we provide a discussion of the implications of our findings for data-driven crime analysis.

keith16

Seems incredible but a sense of inevitability about it.

Can turning your phone off send a signal that you might be about to do something dodgy? I haven't read the whole article by the way.

Rucking_Fetard

keith16 wrote: »

Seems incredible but a sense of inevitability about it.

Can turning your phone off send a signal that you might be about to do something dodgy? I haven't read the whole article by the way.

Nothing about turning off phones in it but really nothing stopping them adding in as a Data point.

I went looking for more on this after, their's a few systems up and running already, You'd never guess where?

Precognitive police

Predictive policing could help prevent crime. But do we want a future where computer oracles and spies track us from birth?

‘There’s a real risk that the data that gets inputted is biased, or based on stereotype or overgeneralisations based on race and class’, said Hanni Fakhoury, a staff attorney at the Electronic Frontier Foundation, a non-profit digital civil liberties organisation in San Francisco. ‘It’s easy to ensnare innocent people into these things. Crooks talk to non-criminals, too, and taking lots of data on some people will inevitably capture information on people who’ve done nothing wrong other than to know someone caught up in the criminal justice system’.

All the systems in the Article already seem geared toward the not white/poor, looking at the wrong class if you ask me.

The comments are good reading.