Is it possible for the police to predict who will commit crimes beforehand? Yes, say scientists who have developed a new software similar to that of Hollywood sci-fi thriller 'Minority Report'.

The software, which will soon be used by law-enforcement agencies in America, may even be able to tell where, when and how the crime will be committed, just as it happened in the 2002 blockbuster.

In the movie, Tom Cruise heads a 'Precrime' unit which uses genetically altered humans known as 'Pre Cogs' to look into the future to prevent crimes before they happen.

It is believed that the software may spark an outcry from civil rights groups for its unmistakable resemblance to the Steven Spielberg-directed movie, the Daily Mail reported.

Developed by Richard Berk, a professor of Criminology and Statistics in University of Pennsylvania, the software collates a range of variables then uses an algorithm to work out who is at the highest chance of offending.

The software is already used in Baltimore and Philadelphia to predict which individuals on probation or parole are most likely to murder and to be murdered.

But now it is being taken one step further in Washington DC to look into the future.

Its developers believe once the trials proved success, the software could be used nationwide to help set bail amounts and suggest sentencing recommendations too.

"When a person goes on probation or parole they are supervised by an officer. The question that officer has to answer is 'what level of supervision do you provide?" said professor Berk.

"It used to be that parole officers used the person's criminal record, and their good judgement, to determine that level. This research replaces those seat-of-the-pants calculations."

The technology sifts through around two dozen variables, from criminal records to geographic location.

The type of crime, and more importantly, the age at which that crime was committed, were two of the most predictive variables.

From a dataset of 60,000 crimes including murder, the research team found a subset of people more likely to commit crime when on parole or bailed.

Compared to the standard murder rate in the US of 1 murderer in 100, they claim to be able to identify eight in 100.

Those who are identified by the software could be subject to tougher bail conditions, or closer supervision -- something attacked by academics as tantamount to harassment.

Their argument is compounded by the fact that currently the software does not provide any direct evidence that a crime will take place.