Boffins reckon they've got the x-factor

 

Gallery

Posted on 11 Dec 2008 at 12:02

Computer scientists claim to have developed a computer model to accurately predict who the next big music superstar will be. They claim that the software can help them identify which aspiring artists who will make it big, before they've even signed a record contract.

The software, developed at Tel Aviv University's School of Electrical Engineering could become a profitable tool for music producers and record labels, according to its developer, Professor Yuval Shavitt.

Shavitt developed the model by analysing data from US peer-to-peer file-sharing network Gnutella. He then devised a computer algorithm that can spot an emerging artist several weeks or months before national success hits.

"Until now, talent scouts for record companies used instinct to predict the next rock personality. Our software has an astonishing success rate about 30 per cent, and in some cases up to 50 per cent. We've crossed a new frontier in the record business," he said.

Shyavitt's system has accurately predicted the rise music stars who have recently emerged including Soulja Boy and Sean Kingston, whose respective hits Crank That and Temperature were both flagged by the algorithm in April 2007, weeks before they emerged into the US spotlight. Both songs became Billboard hits when they entered the US charts in June that year.

Shavitt said that the system has also identified potential stars in the group Shop Boyz who popped up on Tel Aviv University's algorithm radar a few weeks before they signed with Universal.

To develop the algorithm, Shavitt worked with graduate students Tomer Tankel and Noam Koenigstein, to examine a large amount of data from Gnutella user queries for unknown artists over a nine month period during 2007.

By examining the first 6 months' worth of data, and then using the remaining 3 months' data to track the increasing popularity of those artists, they developed a system to predict which artists would break out of their local markets.

"The key was understanding the role of geography in the rising popularity of these artists," said Prof. Shavitt.

The researchers examined the thirty to forty million queries entered each day on Gnutella and found that those artists who eventually made it to the national level first had a huge number of user queries in their local region, even when they had zero queries from elsewhere in the US.

Author: Dawinderpal Sahota