Dr Giovanni Mastrobuoni spent three years evaluating “predictive policing” software in Italy, which he says can reduce crime rates and save forces millions.

An academic from Essex University has spent three years evaluating “predictive policing” software in Italy, which he says can reduce crime rates and save forces millions.

In fact advanced computer software designed to enable the police to predict both the perpetrator and the timing of a crime saved one Italian police force close to £2.5 million euros in jut one year.

That not conjecture – that’s a cold hard statistic, according to the programme’s first ever academic evaluation carried out by a doctor here in Essex.

Dr Giovanni Mastrobuoni from the Department of Economics at Essex University, spent from 2008 to 2011, analysing KeyCrime – a software programme used by the the Polizia, a police department in Milan.

Dr Mastrobuoni focused on KeyCrime’s effects on commercial robberies and found that during the period of the evaluation, the rate of such robberies dropped.

The software works by collecting and analysing around 11,000 bits of information about each robbery – the time, date, location, type of business, type of crime and about the criminals involved – their perceived age, height, body structure, skin, hair, eye colour and clothing.

It also takes into account details about the weapons involved and the type of vehicle involved in the crime, for example the car the criminal fled away in.

This is then combined with police reports, interviews with the victims and surveillance camera footage before using comparisons to establish links in order to identify and predict criminal strategies.

Potential future targets are then communicated to police patrols, together with a likely day of the week and time alongside a description of the offenders, their modus operandi and the transportation they are likely to use.

Speaking about evaluation Dr Mastrobuoni said: “When this advanced yet inexpensive IT innovation is used, differences in police productivity are striking.

“Robbers follow habits. Criminal groups tend to select the same business types, around the same type of day and in the same city or neighbourhood, especially if previous robberies have been lucrative.

“When these habits are properly tracked and identified, that predictability can be put to effective use.

“Moreover, most re-offending occurs within a few days, which means that at any given point in time there is a limited set of unique groups of robbers whose actions need to be predicted by the software.

“When all of this information then becomes available to patrols out on the streets, it puts the police in the right place at the right time.

There is no doubt that this type of micro predictive policing is a highly effective efficient IT investment.”

KeyCrime was created by Mario Venturi, Assistant Chief of the State Police based in Milan, and is still being developed.

Could such software work over here? Well some forms of predictive policing have already been experiemented with in this country.

In August last year Essex Police used a form of predictive software to tackle burglaries in the county.

By predicting the likely location of future robberies, the scheme saw house burglaries fall by 9.8 per cent in just 10 months.