Science & Tech: Big data on crime

By Dr Michelle Dickinson

Big data takes on crime by making reporting easier and predicting future offender patterns. It also helps parties win elections by personalising their pitches.
Auror's cloud-based software allows retailers to quickly upload CCTV images of crimes to police. Photo / Supplied
Auror's cloud-based software allows retailers to quickly upload CCTV images of crimes to police. Photo / Supplied

It wasn't long ago that pushpins were used by police to mark locations on paper maps where crimes had been reported.

Those pins helped police determine if active crime hotspots were forming so they could make decisions about where to dispatch officers to deter repeat offenders.

The average value of a shoplifting incident these days is around $220, and given the time required to report one to police, many retailers don't bother. The Ministry of Justice reports 68 per cent of incidents go unreported, reducing the amount of information police have available.

Lack of reporting has allowed criminals to feel confident they are unlikely to be caught, leading to co-ordinated crime sprees targeting businesses for shoplifting and petrol drive-offs.

This costs us law-abiding citizens serious money with the Retailers Association of New Zealand estimating shoplifters result in retailers losing $2 million a day.

Research shows that the top 10 per cent of offenders are responsible for more than 60 per cent of the total value taken in shoplifting offences and that repeat offenders are likely to strike within 114 minutes and 6.8km of their last offending location.

Predicting an offender's next target would be easier if all crimes were reported to police.

Realising the impact that collecting crime data could have on communities, Kiwi start-up Auror decided to take action and build cloud-based software to create a high-tech crime-fighting system.

The software lets retailers quickly report a theft, reducing the average crime reporting time from 90 minutes to less than 10 minutes, making companies much more likely to report crimes.

By retailers being able to quickly upload CCTV images and add age, sex, ethnicity, height and vehicle details of the suspect, police on the ground can use their digital devices to gather detailed real-time information while neighbouring stores are alerted and informed about the specifics of a suspect in their area.

The software reduces the average crime reporting time from 90 minutes to less than 10.

Preliminary pilot studies with Canterbury and Counties Manakau police have resulted in very positive results, including Operation Shop where Christchurch police saw a decrease in shoplifting for those retailers using the software.

This is the science of big data, in which sophisticated quantitative analysis is used to prevent further incidents by spotting patterns of repeat offenders and helping police to predict where the next incident will be.

Because criminal gangs can move from region to region, Auror has just signed a deal with police to make the technology available to all 12 districts so they can share information across the country.

Research into crime patterns and behaviours is not the only place that big data is having big influence.

The upcoming United States election will be won based on the best big data analysis, with political parties replacing their general broadcast approach to a targeted one using collected personal data. They will initiate conversations with individuals on the topics that matter most to them.

Big data analytics can also decode entire DNA strings in minutes, helping researchers to find new cures while better understanding and predicting disease patterns and epidemics.

As micro-scale data from smart watches and fitness bands is aggregated, soon big data will monitor and predict how individual activity levels affect global health outcomes.

With so many big issues being helped using complex analysing software, it's no surprise that one of the top future jobs is predicted to be in IT as a big data analyst developer.

• Dr Michelle Dickinson, also known as Nanogirl, is an Auckland University nanotechnologist who is passionate about getting Kiwis hooked on science. Tweet her your science questions @medickinson

- NZ Herald

Get the news delivered straight to your inbox

Receive the day’s news, sport and entertainment in our daily email newsletter


© Copyright 2016, NZME. Publishing Limited

Assembled by: (static) on production apcf04 at 25 Oct 2016 12:58:18 Processing Time: 728ms