Catch up on stories from the past week (and beyond) at the Slashdot story archive


Forgot your password?
Music Media

Decoding the Algorithm for Pop Music 353

fb4f writes "Over at Modplug, they have an article describing a mathematical algorithm to predict if a given song will become a hit or not. Paraphrasing the article, a Spanish company called Polyphonic HMI has made a business out of analyzing song submissions and predicting their "hitability". Here's their description of the algorithm and here's their FAQ. They claim to have predicted the commercial success of Norah Jones through this method. Here's my question (which is not fully answered in their FAQ): if they (music company executives) are currently using the algorithm to screen submissions for their "hitability", can we (people who listen to music) use the same algorithm to reject recycled tunes and encourage originality? I for one, still like the fresh talent and community feel of the tracking scene."
This discussion has been archived. No new comments can be posted.

Decoding the Algorithm for Pop Music

Comments Filter:
  • Karma Hit (Score:5, Funny)

    by Aliencow ( 653119 ) on Sunday November 23, 2003 @12:08PM (#7542129) Homepage Journal
    Someone should make an algo to calculate which Slashdot comments will be moderated up to 5. Should be pretty long as you bash SCO!
    • Re:Karma Hit (Score:4, Interesting)

      by bj8rn ( 583532 ) on Sunday November 23, 2003 @12:38PM (#7542303)
      Out of sheer boredom, I actually tried to do this sometime this summer. I took a bunch (something around 20) of SCO stories and read all the +4/+5 comments. Surprise surprise, the overall situation wasn't really as bad as I thought it would be. Yes, there were some patterns in what was said, but even if someone did get modded up for saying something that was obvious they always had some argumentation supporting what they said. Simple bashing might get you modded up for a moment, but you'll be modded down the moment someone posts an intelligent reply.
      • Re:Karma Hit (Score:3, Interesting)

        by MooseGuy529 ( 578473 )

        Someone should make a program that when you ask it to, downloads a story (showing all comments and with the number per page at max so it doesn't have to spider and piss off slashcode) and splits the comments into -1, 0, 1, 2, 3, 4, 5 "buckets" and creates a spam filter. Then, you can apply it to other stories. Sorting by topic would be good, since saying Windows in an Apple story has a good chance of being a flame (or maybe a comparison), but saying it in a story about Longhorn [sucks] probably is less im

        • You're saying a six bucket Bayesian for Slashdot (actually, I'd prefer a nine bucket system - one for each moderation TYPE - bayesian is score based, so filtering at the user end could be done differently - say, 90 as the default hide threshold, but if someone wanted to read ALL messages, set it to 100). It'd only work if the human moderation worked right, though (kinda like humans throwing ham in the spam and vice versa)...
    • by teamhasnoi ( 554944 ) <[teamhasnoi] [at] []> on Sunday November 23, 2003 @12:43PM (#7542331) Journal
      Someone should make an algo to calculate which Slashdot comments will be moderated up to 5. Should be pretty long as you bash SCO!

      It's tough to come up with an algorythm for slasdot moderations. SCO bashing will not guarrentee anything. In fact, I used some software similar to that mentioned in this article, and determined that this comment will be modded +5.

      SCO RULES!
      Bill Gates is your friend.
      I enjoy RFID!
      I can't get enough of that Jon Katz!
      Linux is for little girls.
      Look at my newest casemod! I put a flashlight in there!
      Hilary Rosen is a super-fox!
      I peed in your coffee.
      The Simpsons/Matrix/Starwars/LordoftheRings totally sucks.
      DRM is the answer to everything!
      I just patented food!

      These comments alone would not gain a +5, however, the self-referencial nature of this comment will.

      Granted, this software is still in beta.

      • by aktbar ( 22510 )
        These comments alone would not gain a +5, however, the self-referencial nature of this comment will.

        Was the spelling mistake part of the self-referential nature of the comment?
      • Look at my newest casemod! I put a flashlight in there!

        You have me crying!

  • by anaphora ( 680342 ) * on Sunday November 23, 2003 @12:08PM (#7542131) Journal
    If Singer.Belly.isShown() then mod.singer.+1sexy
    If Singer.Voice.isScreaming() then mod.singer.+1punkfav
    If Singer.Gender.isMale() then mod.singer.+1prepubescentgirls
    If Singer.Label.isRIAA() then mod.singer.+1popular
    If Singer.Style.isOriginal() then mod.singer.-1original

    • by Anonymous Coward on Sunday November 23, 2003 @12:18PM (#7542190)
      Its strangely insightful. I hate bland manufacturised pop music. It's music for the sheeple. I prefer real music from real bands, like Limp Bizkit and Korn and shit like that. Music for us truely individual people who are outcast from society for daring to be different, for refusing to conform, for sticking a finger up to The Man.
      • Re:Mod parent up (Score:5, Insightful)

        by Anonymous Coward on Sunday November 23, 2003 @12:27PM (#7542237)
        one person's "real" band is another person's manufactured corporate rock. Excess ain't rebellion, you're drinking what they're sellin.
      • A quote: (Score:2, Funny)

        by Anonymous Coward

        "Nu-metal is great for 12-year-olds who want to be individual together."

    • I always thought it should be:

      If Act.isFemale()
      then Act.showBellyButton()
      End If

  • what came first? (Score:5, Insightful)

    by garcia ( 6573 ) * on Sunday November 23, 2003 @12:10PM (#7542143)
    Us deciding what is good or the music industry telling us what is good?

    This company's stuff doesn't do much good when society is bombarded by what the industry wants us to hear.

    It becomes a hit because we don't get much of a choice. ClearChannel plays no variety, the non conclomorate channels don't play variety but instead endlessly repeat that they are not owned by ClearChannel and Infinity...

    The only way hits can be decided is through freedom of music.

    Support those artists that support the free distribution, copying, and playing of their music. Start your searchs at Sharing the Groove [] and FuthurNET []
    • Endless Repetition (Score:4, Insightful)

      by TubeSteak ( 669689 ) on Sunday November 23, 2003 @05:23PM (#7543627) Journal
      How many times have you flipped between 2 or more stations and heard the exact same song playing? :Raises his hand: ClearChannel says they play a large variety of bands... and they do! the problem is that each little geographic area listens to a very small portion of those songs (over and over and over).

      The software thats been cooked basically gives record execs another means of increasing their hit:miss ratio.

      So think of it this way, the RIAA claims that they charge high prices to make up for all the flops. They now have a new means to weed out the money wasters. Profit goes up, prices go down... right?

  • I wonder if they've tested it against *other* music than crap as well...

    If Autechre or Pan Sonic came out with extra hitability I guess there'd be a quite few people looking shocked and/or running for the hills... *eg*

    np: Autechre - Gantz Graf (Gantz Graf EP)

    • Re:Hmmm... (Score:3, Insightful)

      by The One KEA ( 707661 )
      The one thing I want to know if whether the music they used to build this algorithm also influenced its basic process and ultimately the algorithm's final result. Wouldn't it be amusing if the algorithm modded up music that was similar to the so-called Top 30 used to construct it and modded down music that was dissimilar to those songs?

      They claim that the algorithm is impartial, but we'll have to wait and see if it really is.
  • Not new (Score:2, Interesting)

    by DrMorris ( 156226 )
    There has been something similiar about 2 or 3 years ago. However: I didn't believe it's success back then, and I don't believe it today.
  • Dupe. (Score:5, Informative)

    by Bootsy Collins ( 549938 ) on Sunday November 23, 2003 @12:14PM (#7542164)

    Well, I don't know how to tell what songs will be popular. But, obviously, this topic is popular [].

    • Ah, I was planning to suggest a filtering program based on similar idea for Slashdot. Then I saw your post and, heck, they haven't even figured out how to filter dupes, sigh!
  • by Lupulack ( 3988 ) on Sunday November 23, 2003 @12:15PM (#7542172)
    40% Action
    30% Comedy
    30% Romance
    0% Madonna

    ( with credit to Jay Leno )
  • by saintlupus ( 227599 ) on Sunday November 23, 2003 @12:17PM (#7542181) Homepage
    They claim to have predicted the commercial success of Norah Jones through this method.

    Am I the only one wondering who the hell Norah Jones is?

    You damn kids and your pop music. I think I'm going to have to dodder out on the porch and yell at the neighbors' kids for playing on my lawn.

  • And my question ... (Score:5, Interesting)

    by rastakid ( 648791 ) on Sunday November 23, 2003 @12:18PM (#7542189) Homepage Journal
    "Here's my question (which is not fully answered in their FAQ): if they (music company executives) are currently using the algorithm to screen submissions for their "hitability", can we (people who listen to music) use the same algorithm to reject recycled tunes and encourage originality?"

    And here's my question: can we use this algorithm to create the hit, instead of determining wether or not it's gonna be a hit?
    • by shufler ( 262955 )
      I don't see why not -- put a song through the program, and based on it's results, make your changes. The FAQ states many times that their software doesn't create music, it simply analyses it. No doubt the record execs are sitting around looking at the analysis, asking, "What needs to be tweaked so more 13 year olds will get their parents to buy this?" (The answer being nothing, as that job is left to the marketing department)
      • Alternatively, run a lot of random noise through their analysis, and publish whatever gets high scores. That's pretty much what record companies do now, and that may be why they find this product valuable. Think how much money the record publishing companies could save if they could eliminate artists entirely!
        John Sauter (J_Sauter@Empire.Net)
    • by wcbarksdale ( 621327 ) on Sunday November 23, 2003 @02:34PM (#7542830)
      Sure, here's a sample run:
      It was only an 'opeless fancy.

      It passed like an Ipril dye,
      But a look an' a word an' the dreams they stirred!
      They 'ave stolen my 'eart awye!
  • Can't be done (Score:5, Insightful)

    by YrWrstNtmr ( 564987 ) on Sunday November 23, 2003 @12:19PM (#7542199)
    Mapping the higher order functions (if there are any) of the teenage and prepubescent female brain is nigh impossible.

    On the other hand, predicting what will be popular might be very easy.
    Next big pop hit = whatever the record companies tell them it will be.

    Witness the last American Idol. Who did the sheeple choose? The large black guy, Rueben. Months later, who do you hear the most about? The Howdy Doody lookalike who came in second place, Clay.

    "you vill like vhat ve vant, not what you vant!"
    • Mapping the higher order functions (if there are any) of the teenage and prepubescent female brain is nigh impossible.

      I didn't know there were any higher order functions ;)
    • personally I think that Clay was supposed to win but the show wanted Rueben to win. The show was fixed to show the more popular PERSON instead of the more talented artist.

      Clay was "good". I don't care for that artsy singing that he was doing but he was far better than Rueben.

      Responding to the AC that posted here as well. Racism? What about equal hatred? Clay as obviously feminine. People in this society do not like those that are feminine anymore than they like those of color. Do you think it made
    • by symbolic ( 11752 ) on Sunday November 23, 2003 @03:03PM (#7542990)

      As a younger listener, I was well aware of rap music, but it sort of cornered its own market and stayed there. I don't think anyone was prepared for, or could of predicted the massive influx of rap/hip-hop into the mainstream. Personally, it's not my bag of tea (little music is these days). And personally, I don't see what's so prolific about it, other than the fact that a good portion of it has a *very* raw, rebellious overtone that is, for whatever reason, favored by youth. But it's there, it has a huge market, and I find it interesting, if for no other reason than to admire the degree of influence it has had.

      Given this, I'm not sure there is any algorithm that can predict what people will decide they like at any given point, as there are so many dynamics at work. As others have pointed out, there is definitely the chance that our music-buying preferences are being manipulated by those at the top telling us what we like. But there are also others - the infamous "what are my friends listening to" I-gotta-be-like-everyone-else mentality. I'd be remiss if I didn't mention another significant consideration, at least with respect to the most of the popular artists: Is there any money in it?
    • >> Mapping the higher order functions (if there are any) of the teenage and prepubescent female brain is nigh impossible.

      Indeed. While scans often show brainwave activity at or near zero, these beings still manage to operate on some preprogrammed level.

  • Classical (Score:4, Interesting)

    by J_Omega ( 709711 ) on Sunday November 23, 2003 @12:20PM (#7542204)
    AFAIK, this isn't new. This technique has been in use for years, at least theoretically.

    IIRC, this was first tested on random samplings of classical music. Beethoven and Mozart scored significantly better that others.

    • Re:Classical (Score:2, Offtopic)

      by Silh ( 70926 )
      Among classical listeners you are more likely to find greater discernment though, especially among people who play instruments... they're likely to enjoy music for which they get a good part. I know some people who really don't like Beethoven too much since the orchestral part they play in his pieces is utterly boring (a commonly seen thing from the classical period forward for supporting parts).

      Some people prefer music from the romantic period, some like more modern fare, and some like myself prefer baroq
      • I don't understand this music thing. They just keep repeating these same twelve notes over and over. Sometimes they will double or halve the frequency, but that's all.
  • by aepervius ( 535155 ) on Sunday November 23, 2003 @12:21PM (#7542207)
    Quote : " What do big hits typically score? As stated above we tend to use 7.00 and higher as a score for a hit song because that's where they tend to score. There have been hits that score a little lower but the promotion has tended to be more aggressive. Some big hits score very low on the HSS scale but more than make up for that low score in other aspects of analyses that a label can do on your music with us if you happen to be negotiating a deal. ".

    It sound like "we found some correlation, but there is data outside the correlation, and sometimes downright anti-correlation between reality and prediction". I think without looking at the data and the real corelation coeficient between "predicting it will be a hit" and "it was a hit" it is difficult to say anything. And even then, correlation between data does not mean there is causal relation, although *pleasing* to the ear is certainly why we hear at music. I think this kleave other factor out. For example the signification of the lyrics. You ear Mozart uniquely for the pure sound pleasantness, but you do not ear some of the rock/pop for its sound only (try it, many of the greatest hit sound "bland" without their lyric).

    Plus even if they try to "reassure" customer in their FAQ, if you comapre things to the past and try to reproduce what has the best functionned in the past, then you will never innovate. Which is IMO the biggest problem now (and it feels that new bands/singer are solely choosen on their look, given prefabricated lyric and tune, and marketed as prima dona, instead of having bands/singer raise on their own by the sheer beauty of their music).
    • I agree, surely they could add another input to their model along the lines of "promotional budget" if they suggest that this is what's causing the outliers?

      On the correlation argument, if they use factors known prior to the song being a hit to predict that it will be, it's not correlation they are looking at but some sort of R^2 - which measures predictability (this is not about causality - they want to PREDICT, not find out _why_). Think of it this way, you can predict in advance that the sun will go d
    • Because in this case there is a causality , not the one you are choosing (darkness provok sun going down) but the other way sun going down provok darkness. In the example of what they give in the FAQ there may not even be a correlation or causality. And to have a prediction better than what the statistical random prediction would be then you have to have a causal relationship between the two. It might be complex it might be indirect transitive (a->b->->...->n) but it has to be tehre. Else you ob
    • Unfortunately, much like the stock market, just because your algorithm *appears* to work on historical data, it's a bit of a leap to the "trade on this algorithm, it'll always make you money" stage. The market always comes up with surprises, mostly because the "market" represents the aggregate behavior of millions of human beings and (more importantly) their complex interactions.

      Similarly, I'm sure with this technology certain patterns are definitely there and can be latched onto, but that doesn't mean y

  • by nuggz ( 69912 ) on Sunday November 23, 2003 @12:21PM (#7542210) Homepage
    People don't want origionality, they don't want something new.
    Occassionally there is a blip and people get excited about something. But mostly they are content to wander through life with a catchy tune in their hollow little heads.

  • Circular logic (Score:3, Insightful)

    by An'Desha Danin ( 666568 ) on Sunday November 23, 2003 @12:21PM (#7542212) Homepage
    So wait a minute.

    The algorithm uses the top 30 songs of the last five years as its base of comparison. It then analyzes thousands of songs and determines which ones are most likely to be hits, and those that score best are selectively fed into the market. These songs by necessity become the next set of top 30 hits, and are again used as the algorithm's base of comparison.

    So basically, the basis of the system is "these songs will be hits because I say they'll be hits, and I say they'll be hits because they sound like songs that I said would be hits." Isn't this a really, really bad (read: dangerous) case of circular logic?
  • by xedd ( 75960 ) on Sunday November 23, 2003 @12:21PM (#7542213)
    It's designed to be a tool for them to protect themselves from mistakes.

    "Well, it bombed in the market, but the software algorithm said it had a chance. I did what the software said was right."

    It's your run-of-the-mill corporate bullshit. No creativity, and no real courage to try something different and take a risk.

    How do you think we got Milli Vanilli? ...And the endless variations of the Backstreet Boys and New Kids on the Block?

    The music industry as it is, is little more than a middle-man. Cut them out of the picture, and the consumers benefit, and the REAL artists do too!
  • by Space cowboy ( 13680 ) on Sunday November 23, 2003 @12:23PM (#7542218) Journal

    Popularity = k . MarketingBudget

    The more they hype it, the more the buying public (increasingly younger teenagers, I wait for the day they get to "pocket-money" kids who simply can't afford it - the industry will implode) will cough up....

    Simon the cynic.
  • Recipe music (Score:5, Insightful)

    by Daniel Dvorkin ( 106857 ) * on Sunday November 23, 2003 @12:24PM (#7542230) Homepage Journal
    Early on in their FAQ they claim:

    Historically, what is pleasing to the human ear has not changed since man began writing music. What has changed are styles, performances, the instruments used and the way music is produced and recorded, but a compelling melody is still compelling ...

    Okay, so far, so good; it sounds like they're saying "good music is good music, and here's a tool for telling whether something is good or not." I'm still skeptical at this point, but it's certainly an interesting idea, and one worthy of study.

    But then they completely lose me with this one:

    A high score means that a song is mathematically similar to recent hit songs and a low score means it is dissimilar. These scores have meaning when it comes to success potential in today's market but is not meant to mean a song is good or bad. For example, when tested for today's market some really great classic hits from the 60's 70's and 80's score very low and would most likely not become hits today with their original production or chord progression. That does not mean that they are not good songs and it is quite possible that if produced more in line with today's sounds they could score much higher.
    IOW, our algorithm says music is good if it sounds like everything else people think is good right now, and if it's different from current Top 40, it's crap.

    They make a high-flown reference to the 36 Plots and other serious attempts at artistic analysis, but that's not what they're actually doing. I do believe that good music is good music, good stories are good stories, etc. I can at least consider seriously the hypothesis that all good art has certain qualities in common, and that by analyzing those qualities we can evaluate a new work's chance of lasting success. But the idea that musicians (or writers, or whatever) can keep pumping out stuff exactly like What's Hot Now and be guaranteed a blockbuster is just stupid.
    • Re:Recipe music (Score:3, Insightful)

      by Ed Avis ( 5917 )
      They make no claim to assess whether music is 'good' or 'crap'. All they try to predict is whether it will sell.

      If 'what's hot now' stops selling in large numbers then the algorithm will be adjusted - presumably they keep feeding in the latest songs and their sales volumes.
      • But they're still chasing their own tail, IMO. They may be able to predict the next Hit That Sounds Like All The Other Current Hits, but they'll completely miss the hits that are successful because they remind people of something they liked a long time ago, or even -- gasp! -- because they're actually original.

        Like I said, I can believe that there's a common thread running through all great music. I just can't believe that the majority of currently successful pop music (not a slam on current pop music pe
        • I agree with you. So much of the stuff currently being released by pop artists is rubbish that I wouldn't give a second thought to. It's all about image and reputation and MONEY, and not about writing new songs that truly appeal to people.

          I find myself liking music from real musicians, people like Celine Dion and Faith Hill. I think pop music is utter crap. Hopefully this algorithm won't be used to stifle the new, fresh, original stuff and pump out the same old crap just to try to make short-term money.
    • Re:Recipe music (Score:3, Interesting)

      by jefu ( 53450 )
      IOW, our algorithm says music is good if it sounds like everything else people think is good right now, and if it's different from current Top 40, it's crap.

      I read that more as "our algorithm doesn't work most of the time, but if we get to rig the test, er, um, choose the musical style we want to deal with, we do ok."

      If they could identify a set of interesting weights (or whatever) that their stuff comes up with, and track those weights over time, then if the time series are anywhere near smooth they co

  • The Manual (Score:4, Interesting)

    by phaxkolumbo ( 572192 ) < minus caffeine> on Sunday November 23, 2003 @12:27PM (#7542234)

    The Manual [] - how to have a number one - the easy way.

    Written by the Timelords (the KLF)

    (i know, this is a bit offtopic, but hey!, why not?)

  • "I for one, still like the fresh talent and community feel of the tracking scene."

    And I, for one, long for the return to the simplicity and elegance of railway travel.

  • by newsdee ( 629448 ) on Sunday November 23, 2003 @12:30PM (#7542260) Homepage Journal
    A few years ago I saw an interview of a "composer" (forgot his name). They're guys who are somewhat famous because their name is in a lot of albums, but in very small print: they compose the actual music that the band plays. This is standard practice, apparently.

    Anyway the point is that the guy pointed out that most pop tunes were rehashes of older pop hits. Maybe you create a different style with different instruments or beat, but the underlying melody is the same. He then showed some examples, in how some modern R&B titles were lifted off some older Rock titles. It's not that hard to believe though, look at how Puff Daddy makes a living out of talking fast over music of old hits.

    So in short, one way to predict if a music will be a hit is by creating a database of previous hits and test the correlation...

    [and then of course, there's those who say that Classical music tried every combination possible, so nothing can be new afterwards - but that's maybe a little extreme].

    • Perhaps they're right... to my ear, punk owes a lot to the heavier classical stuff, in terms of how the music hangs together structurally. This probably explains stuff like Mike Batt, that can't decide if it wants to be classical or hard rock [g]

      (PS. I'm a big fan of Mike Batt. :)

    • Copyright (Score:2, Interesting)

      by yerricde ( 125198 )

      Anyway the point is that the guy pointed out that most pop tunes were rehashes of older pop hits.

      And this is how the situation perpetuates itself. If somebody new to the scene comes in and tries to write an original song, he will undoubtedly get bit by an earworm of a song that was popular decades ago but is still copyrighted. Then the older song's publisher will sue the rookie.

      Yes, it could happen, and yes, it did happen: Bright Tunes Music v. Harrisongs Music [].

      and then of course, there's those

    • by iabervon ( 1971 ) on Sunday November 23, 2003 @01:49PM (#7542622) Homepage Journal
      It's certainly possible that classical music got all of the interesting underlying melodies. But the importance of style and instrumentation shouldn't be ignored (let alone lyrics). Interestingly, most currently available recordings of classical music are done by taking the underlying melody and playing it in the most boring way possible, which is rather different from how the scores were originally played. It's a bit like the works of Shakespear being read by a computer in a totally flat voice, except where the script actually specifies that the character whispers or shouts. Popular music is played (and was always played) with a substantial amount of interpretation by the performers, which forms the style.

      Furthermore, I think that the style, and, especially, working out how the style and the underlying melody can be resolved, is as significant an application of artistic talent as writing the melody in the first place. It's like translating poetry; it's easy to do a direct translation, but making it actually work as poetry in the target language is at least as hard as writing the original (since you're constrained not only to write a good poem, but you have to also make it match another work in all of the ways that are important, while using entirely different grammer and vocabulary).

      In short, even if classical music tried every melody, the existance of new styles and instrumentations means that there will be new complete works.
      • even if classical music tried every melody, the existance of new styles and instrumentations means that there will be new complete works.

        I fully agree. But if innovation is on style and instrumentation, and those remain constant across songs of a same "pop style", then they're not innovative at all. Maybe the first one of them, but that's it. As for the actual content of the lyrics, most pop songs seem to fall into one of these patterns:

        - "boy/girl loves girl/boy"
        - "angry against the 'system'"
        - ego trips
  • Snake oil? (Score:5, Interesting)

    by Xzzy ( 111297 ) <> on Sunday November 23, 2003 @12:33PM (#7542272) Homepage
    The article states:

    "This software will compare the song to a database that contains the "top-30" hit songs of the past five years in order to search for mathematical similarities. The algorithm then assigns each song a score between one and 10. Any song rated more than seven is likely to become a hit."

    Now think about this.. use musical eras like the 80's and early 90's as an example because it's reasonably safe to assume this technology didn't exist at that point.

    Look at the charts in 5 year chunks, it all sounds the same. In the 80's, everyone either used a synthesizer or had a raging, face-melting solo at some point in the song. Or the early 90's, "grunge" was being pounded into our head incessantly.

    It was like that because it was popular. Band X makes it big, and suddenly Bands X1 through X255 appear on the charts mimicing this sound. This seems to happen in, amazingly enough, cycles of 5 years.

    Seems to me this software does nothing to show the "hitability" of a song, but rather telling you whether or not it sounds just like what's currently popular, and has been for the past couple years.

    Seems about as magical to me as as an algrorythm claiming it can detect boys that like looking at porn.
  • Um... (Score:5, Funny)

    by cjpez ( 148000 ) on Sunday November 23, 2003 @12:33PM (#7542277) Homepage Journal
    They claim to have predicted the commercial success of Norah Jones through this method.
  • It's not so much that the algorithim can determine that the song will be a hit, it's that the algorithim picks a song apart and lumps it with similar songs - whether the similar songs were or are hits is what determines whether a given specimen will make it onto the Billboard charts.
  • Here's my question (which is not fully answered in their FAQ): if they (music company executives) are currently using the algorithm to screen submissions for their "hitability", can we (people who listen to music) use the same algorithm to reject recycled tunes and encourage originality?

    I really hate to even remotely sound like I'm going to defend the music industry, but: Why don't you decide for YOURSELF without any help from your peers or technology as to the merits of the music? All music is just nois

    • no one is forcing you to listen to a "Clear Channel" type station in the first place.

      How about every employer in fields where employees do not telecommute? If all the music stations that one's car can receive are owned by Clear Channel or another nationwide radio giant, what other choice is there to listen to while driving to and from work?

      • There are at least two controls on every car radio. One of them changes the station, and the other turns it off. You can also opt to bring your own pre-recorded tunes on cassette or CD if your car's audio has the capability. As a last resort, you may try whistling a cheerful tune.

        Now there is the uncomfortable environment that I didn't anticipate from my original post: Canned music in department/grocery stores. The employees in those environments have no choice but to listen to music played overhead. On t

      • Car Radio? What's that?

        My old car had a Radio/Cassette deck, into which I had plugged one of those CD-Tape adapters. After a few years, I could no longer eject the adapter and was (gasp) forced to only listen to CDs.

        In the past 5 years, the only radio station that I've listened to is NPR. My new car has an MP3 CD player, so with the 10 CDs stuck in the visor and the other 20 in a carrying case, I have around 300 hours of music to listen to.
  • My (somewhat vague) recollection is that Kurt Vonnegut's (originally rejected) PhD thesis looked at the plot lines of many books, using the X axis as time and the Y axis as good fortume or bad fortune for the principle character. It turned out that there were only a few graphs that led to best-sellers; any books that tried a different tack were not popular. (Except possibly for Shakespeare; Vonnegut mentioned that he could never figure out what was good- or bad-fortune in a Shakespeare play).

    It may simpl
  • by wytcld ( 179112 ) on Sunday November 23, 2003 @12:43PM (#7542334) Homepage
    Those of us who were listening to pop music during the 60s enjoyed continuous creativity from many different directions, all going directly into widely popular stuff. Then the music marketing business got its formulas - its algorithms - together in the early 70s and there hasn't been a similar sustained wave of pop culture creativity since. The difference in the 60s, in large part, was that the record companies had seen their old formulas largely stop working about when the 60s began, and so were left to their resourcefulness in finding good stuff beyond their former formulaic sensibilities. By the time the 70s came, a younger generation of music executives had come in who could distill formulas from the prior decade of experience and render rock-based pop largely morbid, as swing-based pop tunes had become by the 50s.

    Those of us who live by algorithms should recognize that there are some sorts of human creative intelligence which cannot be captured by formulas, or replaced by them (see physicist Roger Penrose's books on this). If something like this firm's algorithm is really accurate, it should be possible to evolve a neural net to compose pop songs simply by having the success of its efforts defined by feedback from the formula. Would you find living in that world inspiring?

    Much of the best of 60s pop music was haunted and quirky. That's what happens when the creative is in the lead, rather than the formulaic. Compare the Elizabethan stage. Human expression triumphs when the formulas, while still there for reference, cease to have a stranglehold over production.
    • Would you find living in that world inspiring?

      Certainly not inspiring, but I don't see why it should be any worse than today's world of N'Sync and comparable test tube bands.

    • It is interesting that you mention the 50's-vintage swing-pop at the time of the rock-n-roll revolution.

      Is it safe to say that Lawrence Welk was also a 60's phenomenon? I have a mom in a nursing home, and the PBS showing of Lawrence Welk reruns is the Saturday evening "activity" at that and many other nursing homes. One of my hidden pleasures is actually Lawrence Welk because they did a lot of cool swing-pop.

      Heck, what made Lawrence Welk, well Lawrence Welk, was that he was doing swing-pop long after

  • I've long thought that the reason that I disliked most of what passed as ``popular'' music was that it was too formulaic. I used to think it was just ``herd think'' by music industry executives but now it turns out that they've just been following a recipe and these guys just reverse engineered it.

    How long before I can get a box that I can connect to the stereo that displays the level of adherence to The Formula so I can get a visual indication of why I dislike a certain song and can change the station.

  • Saw this on TLC/Discovery a while back. Basically, what they found were that popular music generally were grouped together like star constellations. So what you had were good music grouping together.

    Indeed, original music isn't necessarily good. But what was interesting was that in the report, they talked about all the different genres, and even older music, like classical, held true to grouping.

    And even music in the same category, like two Pop songs, weren't always in the same grouping.

    On another not
  • As everybody knows, in the current payola scheme, songs with three commas in their name get automatic airtime.
  • by dcuny ( 613699 ) on Sunday November 23, 2003 @01:18PM (#7542509)
    • As the market changes, the system reflects this by finding new patterns in the hit clusters and applying these to the process.

    So let me get this straight: if a song sounds like a current hit song, it may well be a hit song?

    Any this is useful how?

    They say they match parameters such as:

    • Melody
    • Harmony
    • Chord progression
    • Brilliance
    • Fullness of sound
    • Beat
    • Tempo
    • Rhythm
    • Octave
    • Pitch
    This isn't "analysis", it's gross categorization (i.e.:"uptempo pop song in the Michael Bolton vocal style"). It's entirely subjective to the listener - what does "fullness of sound" mean, anyway?

    Even then, they add this huge disclaimer:

    • BUT there is a major caveat: There are three factors to making a hit song:

      1. The song must be good from an A&R perspective. That is it must sound like a hit song to human ears.

      2. It must have optimal mathematical patterns. (that's where this service comes in).

      3. It must be promoted well and with an appropriate artist.

    Feh. Nothing to see here. If you're interested in real algorithmic analysis, check out David Cope [].

  • Rebel to Rebel? (Score:3, Insightful)

    by __aagmrb7289 ( 652113 ) on Sunday November 23, 2003 @01:19PM (#7542514) Journal
    Personally, I listen to music I like. If I don't like it, I don't listen. If that means I happen to like the music of the latest "pop sensation", well, that's not a problem. So this idea of rejecting music that fits this profile? Not for me, and shame on you - if ya'all would just be true to what you like, then perhaps this whole thing would be less of a problem.
  • Damn it's really simole:

    Verse 1
    Verse 2
    Verse 3
    (Repeat chorus while fading out)

    There. A top ten song...
  • Utter garbage. (Score:4, Insightful)

    by Gray ( 5042 ) on Sunday November 23, 2003 @01:34PM (#7542564)
    "Historically, what is pleasing to the human ear has not changed since man began writing music."

    That's true in that music has probably had percussion since the start, other then that, total rubbish.

    What about music from other cultures? Totally different scales, numbers of notes, structure, the works. You gonna tell a billion Indian's their taste in music is mathematically wrong?

    Music is almost 100% relative. It's about painting a psycho acoustic picture inside the listener. Why do certain sounds feel aggressive, well others are soulful? It's 99% arbitrary.

    Goodness, in a pop sense, is a matter of painting a picture a whole bunch of people perceive in a similar way. It's a function of civilization, just like any art.

    The very thought that you can mathematically write pop songs. People have been trying for awhile. Even if you get an algorithm for a perfect pop song, everyone would get sick of that style and pop would reinvent itself. It's what happens. Hair metal gives way to Grunge. Grunge gives way to Big Beat, Big Beat gives way to nu metal, nu metal gives way to retro-punk. Hip hop does it all within one genera. Street goes to bling, bling goes to conscience, conscience goes to freestyle street and now we got Outkast doing some sort of 70s funk thing doing triple platinum.

    The trick isn't writing songs, that's easy, the trick is writing the songs that work nearly universally.
    Ask anybody who does it for a living.

  • Did they include the size of the singer's boobs in their algorithm ?
  • Wesley Willis figured out the algorithm for Rock & Roll Music a long time ago.

    After listening to a lot of Wesley Willis mp3s, the Beach Boys start to sound very formulatic, complete with the exact same pattern: Verse Verse Solo Verse. Only without the chorus consisting of repeating the title 4 times.
  • by theoddball ( 665938 ) < minus language> on Sunday November 23, 2003 @02:11PM (#7542722)
    Rivers (that enigmatic, endearingly geeky Weezer frontman) has been doing this for years, by himself. He has notebooks and notebooks filled with his mathematical analyses of many of the biggest pop and rock hits ever written.

    Appears to work (or at least teach him a pattern)--Weezer's damn catchy.

  • balancing on a rope (Score:3, Informative)

    by pohl ( 872 ) on Sunday November 23, 2003 @02:12PM (#7542729) Homepage
    I used to complain about the recycling of musical ideas up until the point where I engaged in a serious study of the theory of harmony.

    It turns out that there just aren't that many ways that you can assemble the harmonic building blocks of music (in mere structural terms, that is -- the treatment of the structure is where the real variety goes). What I mean is that we have to live with the cycle of fifths, and the strong progressions that happen between chords rooted on tones that are adjacent in the cycle. Why? Because the root tones of the chords in your "key" all happen to be adjacent along the circle, as are the remaining 5 out of 12 tones that are not in your key.

    The I (roman numeral one) chord has the IV chord on one side, and the V chord on the other. There's your basis for rock and blues.

    On the far side of the V chord (from the I) lies the ii chord (lower-case roman numeral, denoting a minor chord). There lies your basis for jazz: the ii V I progression.

    And the longest, strongest progression that contains all of the diatonic chords: IV vii iii vi ii V I (473-6251). They're all in a line along the cycle of fiths, except between the 4 and the 7, where we hide the "seam" left by restricting ourselves to the diatonic tones.

    And why restrict ourselves to the diatonic system? Well, it turns out that the diatonic major scale is unique in that it can be constructed by a simple algorithm, starting with one of the 12 tones (adding to the scale as you go) and proceeding up a perfect fifth (modulo 12) until there are no more gaps left that are larger than a "whole step" (two half-steps). This is a very special scale and it amazes me how early in human history it was discovered. It's no wonder the monks thought it was god's own scale.

    And don't even get me started on the golden ratio as it appears in musical architecture.

    Of course music gets recycled. Deal with it.
  • Whats that experiment? Shrodingers cat?

    By observing the object, the object changes.

    One example of this is the trillion dollar bet [] where the only way to protect against such misuse or stockmarket card counting, is to make it public where everyone uses it.

    Something about making something untrue by making it public knowledge.

    If such a algorythim is possible then it can be programmed into a music program to generate intellectual property...So to own all hits before they are.

    Maybe we just need plugs in the
  • oops--wrong forum


  • by Threed ( 886 ) <nowhere@[ ] ['ata' in gap]> on Sunday November 23, 2003 @02:50PM (#7542910)
    TITLE OF THE SONG - DaVinci's Notebook

    Declaration of my feelings for you
    Elaboration on those feelings
    Description of how long these feelings have existed
    Belief that no one else could feel the same as I

    Reminiscence of the pleasant times we've shared
    And our relationship's perfection
    Recounting of the steps that lead to our love's dissillusion
    Mostly involving my unfaithfulness and lies

    Penitent admission of wrongdoing
    Discovery of the depth of my affection
    Regret over the lateness of my epiphany

    Title of the song
    Naive expression of love
    Reluctance to accept that you are gone
    Request to turn back time
    And rectify my wrongs
    Repetition of the title of the song

    Enumeration of my various transgressive actions
    Of insufficient motivation
    Realization that these actions led to your departure
    And my resultant lack of sleep and appetite

    Renunciation of my past insensitive behavior
    Promise of my reformation
    Reassurance that you still are foremeost in my thoughts, now,
    Need for instructions how to gain your trust again

    Request for reconciliation
    Listing of the numerouss tasks that I'd perform
    Of physical and emotional compensation


    Acknowledgement that I acted foolishly
    Increasingly desparate pleas for your return
    Sorrow for my infidelity
    Vain hope that my sins are forgivable
    Appeal for one more opportunity
    Drop to my knees to elecit crowd response
    Prayers to my chosen deity
    Modulation and I hold a high note...

  • by Awptimus Prime ( 695459 ) on Sunday November 23, 2003 @02:53PM (#7542930)
    "if they (music company executives) are currently using the algorithm to screen submissions for their "hitability", can we (people who listen to music) use the same algorithm to reject recycled tunes and encourage originality?"

    No. You don't have a say in this and you know it. Why ask? The industry is fueled by american teenagers. They aren't the wisest shoppers, nor the most picky. Give them a set of boobies to admire and some bling bling to think about and out come the $20's.

    An example: Brittney Spear's popularity. 12 magazine covers and over 20 tv appearances this month alone. Who reading this actually buys her CDs? Probably not many, she's a manufactured star for highschool kids.

    I do wish the sound of a 'band' would become popular again. It seems like ever since the alternative explosion in the early 90's every white-bread band has to sound the same. Can one male singer (not hiphop) NOT sing through his nose for a song or two? That, and the heroin voice (ie. Faith No More) is so damn overdone. What are we up to now? 5 or 6 top 40 bands that might as well have the same vocalist and guitarist? There must be some algorythm that picks up on this in the 'hitability' analysis.

    This isn't anything new, I guess. It's like that Monkies tv show modelled after the Beatles. Except now, it's not a tv show and it's got a lot of re-runs. /gripe
  • This is totally incomplete because it omits 90% of what makes a pop artist a hit. It's all about the dancing, attititude, self-groping, clothing, and sex-appeal.
  • Why is it so foreign a concept that humans would prefer certain subsets of frequencies, dynamics, chord progressions, and so on?

    If someone does end on the tonic, it's going to frustrate a piece, for example. It doesn't take a learned audience to notice this, but a trained audience will realize why the piece doesn't sound finished. (The tonic is the first note in the scale a piece is in.)

    The blues is formulaic. It sticks to the same chord progressions. Rock sticks to a similar set of chord progressions.. T

Every nonzero finite dimensional inner product space has an orthonormal basis. It makes sense, when you don't think about it.