YOUR ALGORITHM SUCCESSFULLY PREDICTED CRIME IN US CITIES A WEEK BEFORE THEY HAPPENED. HOW DID YOU BUILD THE ALGORITHM?
The city of Chicago and the seven other cities that we looked at have started putting out crime event logs in the public domain. In Chicago, these are actually updated daily with a week's delay.
These event logs contain information about what happened, what type of crime it was, where it happened, the latitude, longitude, and a timestamp. In Chicago, we also have information about if there were any arrests made when there were interactions with the police officers.
So we start with this event log and then digitise the city into small areas of about two blocks by two blocks about 1,000 feet [300 metres] across.
And in one of those tiles, we'll see this time series of these different events, like violent crimes, property crimes, homicides and so on. This results in tens of thousands of time series that are coevolving.
What our algorithm does is look at these coevolving time series, then figures out how they are dependent on one another and how they're constraining one another - so how they're shaping one another. That brings up a really complex model.
You can then make predictions on what's going to happen, say, a week in advance at a particular tile, plus or minus one day. In Chicago, for example, today is Wednesday. Using our algorithm, you can say that next Wednesday, on the intersection of 37th Street and Southwestern Avenue, there would be homicide.
HOW DO YOU ENVISAGE THE WAYS YOUR ALGORITHM COULD BE USED?
Denne historien er fra Summer 2022-utgaven av BBC Science Focus.
Start din 7-dagers gratis prøveperiode på Magzter GOLD for å få tilgang til tusenvis av utvalgte premiumhistorier og 9000+ magasiner og aviser.
Allerede abonnent ? Logg på
Denne historien er fra Summer 2022-utgaven av BBC Science Focus.
Start din 7-dagers gratis prøveperiode på Magzter GOLD for å få tilgang til tusenvis av utvalgte premiumhistorier og 9000+ magasiner og aviser.
Allerede abonnent? Logg på
CHANGE THE (BODY) CLOCKS
Why the end of British Summer Time can be a wake-up call for our circadian health
ARE OCTOPUSES SENTIENT?
If you've watched the Netflix documentary My Octopus Teacher or been lucky enough to encounter an octopus in the wild, you'll know there's something special about them.
THE MEXICAN MOLE LIZARD
Imagine what would happen if an earthworm, a lizard, a snake and a mole went on a night out, had too much too much tequila and let their guard down.
Do we finally know how the Egyptian Pyramids were built?
A number of breakthrough studies are beginning to paint a picture of how these wonders of the world were built, but much of the story still remains a mystery...
ECLIPSES ON DEMAND
Inside an unassuming building, behind a damp car park in Antwerp, Belgium, scientists are teaching two spacecraft to be dance partners for a performance that will take place in front of the Sun.
How light's 'secret code' reveals the story of the cosmos
The starlight we can see tells us alot about the Universe, but it's the parts we can't see that contain the biggest revelations
An artificial heart inspired by plumbing
Mechanical circulation could revolutionise transplant design and reduce waiting lists
Major Stonehenge discovery deepens mystery around ancient monument
New findings suggest a key six-tonne stone came from over 450 miles north of the circle
THE UNEXPECTED RETURN OF PNEUMATIC TUBES
Once a pioneering technology that revolutionised deliveries, pneumatic tubes had all but disappeared. Now they're back and enjoying a resurgence
LIVING FOSSILS
FOR SOME CREATURES ALIVE TODAY TIME HAS ALMOST STOOD STILL. MEET THE 'LIVING FOSSILS' THAT GIVE US A GLIMPSE INTO LIFE IN THE DISTANT PAST