mobile-bannertablet-bannerdesktop-banner
TIDAL X: 1020 Amplified by HTC - Show
Beyonce (L) and Nicki Minaj perform at concert for the Tidal music streaming service in Brooklyn on October 20, 2015. Jamie McCarthy—Getty Images

Can an Algorithm Discover the Next Beyoncé?

Dec 15, 2015

Imagine that the next Beyoncé Knowles is living in a small town in Lithuania, making music videos in her bedroom.

In the music industry's heyday, young Bey would have to go to local clubs and talent shows to show off her singing skills. With luck, a record label executive would be in the crowd, where he would take a shine to her, bring her in to perform for the label's president, and eventually be signed to a recording contract.

More recently, young Bey would upload her music videos to the Internet, where she, with luck, would be noticed by a music executive and eventually signed.

But what if an algorithm could scour the Internet for that executive? What if data analysis could reveal the next big star well before she played the local bar—and allow a music manager in Los Angeles to instantly sign her?

Thanks to big data and an algorithm developed in France, it's possible.

Improbably named “Elise,” the algorithm was created by Quentin Lechémia, 25, a clean-cut, fast-talking millennial from Lyon. Part rocker, part geek, he oversees a staff of eight at his startup's office in Paris, surrounded by computers, vintage vinyl records, and the odd guitar. (In his free time, Lechémia plays in an indie pop duo called Destronics.)

The company's name? My Band Market.

Lechémia first had the idea for Elise in 2011 when he was pursuing an accounting degree in London and working part-time at a music studio on the legendary Tin Pan Alley.

“I met a ton of musicians," he says. "And all of them shared an interesting problem: whether amateur or semi pro, they never knew their own value.” When bands were hired to play live, they rarely knew what to charge, he says. Many were simply paid in beer.

He decided to develop a pricing system based on each musician’s online popularity. A self-taught coder, he returned to France and created his company on top of an algorithm that collected Facebook data on emerging musicians—how many fans, comments, etc—then assigned a monetary value to each one.

He launched a blog to help promote the Elise platform, and was surprised to see traffic spike at any mention of up-and-coming talents. So he decided to take the algorithm further by creating a scoring system for musicians’ popularity based on three online sources: social media, streaming media, and mentions in the press.

Elise now trawls the web for data from Facebook, Twitter, YouTube, Spotify, and Deezer. It tracks keywords for mentions in the press, giving a higher score for more influential media sites. It will soon check for reports of live concerts and audience size.

Mining and analyzing billions of pieces of digital data, the algorithm ascribes each musician or band a score out of 100 within its particular category, taking style and geographic location into account. "A Japanese musician who does K-pop might have a super score in Japan but not necessarily in France," Lechémia explains.

He says the technology behind Elise is so comprehensive that the company can use it in a variety of ways.

One option is to sell its utility to other corporations. By licensing access to its database, My Band Market helps music labels (including giants Sony and Universal) search worldwide for the next big star. It works with communications agencies and corporate clients (such as Converse and Audi) to source the ideal little-known musician to promote their products, and at a much cheaper rate than established performers.

Elise doesn't just spot musicians on the rise. It can also determine their target audience by age, sex, and location. “It’s incredibly precious data for brands,” Lechémia says.

The algorithm also comes in handy for derivative products. Lechémia says his blog, My Band News, has become one of France’s top music webzines because it’s the first to talk about emerging musicians.

In 2014, Elise picked up on the Generation Y’s lousy opinion of the annual Eurovision Song Contest, based on tweets and posts. “People were incredibly critical,” Lechémia says. “We thought, why not create our own Eurovision, using new technology?”

His EuroMusic Contest featured contestants from 40 different countries, a livestreamed finale and online voting in real time. (In 2011 he experimented with a simpler version of the same.) He says it generated 350,000 votes and more than a million unique page views in one month.

Just afterwards a major French TV producer came calling, and along with other investors, injected a quarter million euros in capital into My Band Market. The French public investment bank, known as BPI, loaned it another €250,000 for R&D.

The potential payoff for investors is high in an industry where big data is becoming indispensable. “Data is a major preoccupation,” says Daniel Findikian, a consultant for the music industry who formerly ran the new technology department at EMI France. “Collecting and controlling your own data has become essential for making musical recommendations.”

In 2014, Spotify bought Echo Nest, an algorithm that deciphers musical tastes and proposes songs, for a reported 100 million dollars in cash and equity. Early this year Apple acquired Musicmetric, a startup providing real-time music analytics, reportedly for around $50 million. Afterwards, Pandora picked up Next Big Sound, an analytics company that tracks social media and streaming.

Lechémia says Elise has features the others lack, such as the scoring system and geo-localization. In the future he wants to integrate “emotional” data, or how a band makes its audience feel at a live concert, though he won’t reveal how he plans to go about gathering this.

Currently My Band Market is holding another round of fund raising and working on a new subscription model for the end of the year that would allow clients to input criteria and search for emerging artists anywhere.

As for his own musical career, Lechémia chooses to make it a sideline, though his duo is releasing its second album this year. (A true serial entrepreneur, Lechémia also found time to develop a pornographic version of Instagram called "Uplust." It receives 1.5 million views a day, most from the U.S.)

When I ask what score his music group gets from Elise, he says it’s 58 in France. Destronics’ most recent video clip is called “Look.” If enough people do so, the band just might break 60.

Next, read: The (very) big fight for the small screen

Subscribe to Data Sheet, Fortune’s daily newsletter on the business of technology.

For more on the music industry, watch this clip from Fortune's Brainstorm Tech conference:

All products and services featured are based solely on editorial selection. FORTUNE may receive compensation for some links to products and services on this website.

Quotes delayed at least 15 minutes. Market data provided by Interactive Data. ETF and Mutual Fund data provided by Morningstar, Inc. Dow Jones Terms & Conditions: http://www.djindexes.com/mdsidx/html/tandc/indexestandcs.html. S&P Index data is the property of Chicago Mercantile Exchange Inc. and its licensors. All rights reserved. Terms & Conditions. Powered and implemented by Interactive Data Managed Solutions