“They know what songs you like, even before you like them. Record labels spend millions of dollars each year trying to predict what singles will top the charts and which ingredients make a hit single. Now, two Massachusetts Institute of Technology PhD grads believe they have cracked the code,” Grant Robertson reports for The Globe and Mail.
“After years of crunching data, Brian Whitman and Tristan Jehan have devised a computer program that listens to a song, then predicts how humans will react to it,” Robertson reports. “The response is so specific at times that it can forecast how a single will perform on the charts and spit out a review, guessing what words will be used to describe it, from ‘sexy to romantic to loud and upbeat,’ Mr. Whitman said.”
“The MIT method, developed at the school’s renowned Media Laboratory, also takes into account social responses to hit music that are fed into the algorithms,” Robertson reports. “The researchers pull data from weblogs, chat rooms and music reviews — anywhere a song is being discussed — and feed it into the computer, which allows the software to gauge the popularity of a certain sound. Once all the information is tabulated, the computer can listen to an entirely new album and predict how people will respond based on what it knows about the latest reactions to the music it has already heard.”
Robertson reports, “If it sounds far-fetched, consider this: the system has been predicting Billboard hits with surprising accuracy over the past several months. While people may think their musical tastes are unpredictable and whimsical, they are actually quite traceable, Mr. Whitman says. The researchers’ goal is to revolutionize the tracking techniques used by companies such as Amazon.com and Apple Computer Inc.’s iTunes music store. Those companies compare similarities between songs, add in the buying history of consumers, then recommend albums that each person should buy. Mr. Whitman and Mr. Jehan, who are both musicians, scoff at those methods.”
Full article here.
Advertisements: The New iMac G5 – Built-in iSight camera and remote control with Front Row media experience. From $1299. Free shipping.
The New iPod with Video. The ultimate music + video experience on the go. From $299. Free shipping.
Um, could these two MIT guys concentrate next on something of real value…. like predicting next Saturday’s winning lotto numbers or something? ” width=”19″ height=”19″ alt=”tongue wink” style=”border:0;” />
Computer, play me a song that you know I will like!
Still no recommendations on my iTunes. Guess the thing just won’t work on me.
Maybe for the average person. The average person does not like music. Sure, they would reply, “I do SO like music! See, I’ve just bought the “Best of Bon Jovi” cd! that’s music, right?!”, but the fact is they don’t. Most people listen to and buy whatever crap is put on the top 40 charts and/or radio airwaves. These MIT guys can probably predict what they’ll like simply by asking the major labels which releases they plan to spend the most for advertising on in the near future. For those of us who love music and would rather die without it, there will be no program that can predict our tastes.
just another example of how music is so corprate and not about the musicans and the actual music they play
I believe Mr. Whitman and Mr. Jehan, who are both musicians. After all they go to MIT, and isn’t Zenator Kennedy from around zat keneck of the voods, and who vouldn’t belief zuch a good svimmer?
I wonder if this program takes into account how large the singer’s boobs are, or the backroom payola dealings the record co’s engage in.
Uh………….. ok…………..
but who really cares?
~Caleb
Cunning linguists need this done on a global scale. Some of my favorite artists aren’t very prolific, and I’ve more apetite for their sound. iTMS also needs to go global as I find little of interest in my domestic iTMS.
And on that subject, how about trashing dvd regions? Say you read a recent article about the Korean “Break Through” on one of the popular weekly mags where there’s a reference to a hit movie [Taegukgi]. Can you ask a Korean friend to buy you the dvd if your drive is of another region? Can you get it locally? With al these barriers, industry greed and lack of vision [including SONY’s stupidity], no wonder p2p thrives.
Porn and p2p are catalysts for change. Instead of seeing them as threats, more-vanilla-like industries need to read them as signs of a paradigm change, and look at them as opportunities to learn how to surf the wave of change rather than wallow in its wake splashing threats and epithets.
Or you can just ask Steve Jobs. Do you understand, for example, the wide ramifications of tiered pricing? You could end up discounting your legacy titles and diverting new titles towards p2p — a lose-lose situation.
MW: “feel” as in, “I feel your confusion.” C’mon, give Steve a call.
Now can you do the reverse. Using the prediction of program backwards so that it write hit singles all the time. Gee imagine a band using that, with the guarantee that each song will be a hit single.
MIT formula for top 40 hits:
(radio repetitions) x (# of skanks in video) x (marketing cash outlay)
———————————————————
(# of people who have decent musical taste)
It could work. I know that I like syncopated rhythms. A program could pick up songs that have syncopated rhythms and recommend em to me.
Good, now run that Rap shit they call music through this gizmo, and it will delivery the following result:
WARNING … WARNING … RAP DETECTED … RAP DETECTED … WHAT A PIECE OF SHIT … WARNING …
“Record labels spend millions of dollars each year trying to predict what singles will top the charts…”
Sure they do.
Now we know why music has been so bad lately.
This software could never make predictions about breakthrough artists, like Elvis, Bob Dylan or Jimi Hendrix, because the software lives in the past.
I’d be very happy to see Apple use the Pandora technology (pandora.com) in their iTMS setup.
This is Mac news?
if you don’t like my music, i’m a bust a cap in your azz
SKEET SKEET SKEET SKEET SKEET
Of course.
The “hits” are crammed down people’s throats, and just like with TV, movies and computers, most are afraid to try anything different.
Im concerned about that type of technology, seems like it will prevent a lot of artists from experimenting. Ive liked lots of songs that they never or rarely play on the radio. Record labels listen now, if you want to make consumers happy just allow us to pay for downloads of high quality tracks and burn our own cds, but we need longer than 30 second previews in general.