iPod

This post will (temporarily, at least) close the loop my recent discussion of good music prediction systems.

One service that initially escaped my attention was Last FM, aka AudioScrobbler. Perhaps it went unmentioned because it’s a bit of a hodgepodge when it comes to features – it tracks what you listen to, but compiles only the vaguest (and in my experience, often incorrect) statistics about your listening habits. It features some free music, but not in a predictable enough fasion that i’d use it on a regular basis.

Since it doesn’t accumulate anything but playcounts, Last.fm can only predict based on your listening habits. For someone like me who listens to 1k+ tracks a month, the approach is fascinating but ultimately scattershot, as it isn’t weighting my likes and dislikes at all. Though it has the plus side of offering predictions based on a large network of users who you can either friend or “neighbor,” the lack of any rating scheme is a major turnoff.

That said, i return my attention to Yahoo’s LaunchCast Radio.

I have been phasing this out at work now that I have a new iPod, and it’s unaccessible at home since it doesn’t work in Firefox. However, i remain convinced that it comes the closest to being the best music service out there based on the strength of its predictive abilities. It has lead me to more than a few downloads and purchases in the last month, many of which have been surprisingly obscure.

I definitely recommending trying the service, and do so with the following recommendations:

• When you first subscribe spend a day or two listening to one of the pre-set stations that’s nearest to your tastes in order to give the service some ratings to work with. Alternately, take a sampling of your record collection and add 200-500 ratings – probably enough for the services correlative powers to kick in.
• Unless you enjoy a *wide* swath of music in one particular genre it’s in your best interest to rate genres very conservatively, especially high-level buckets like “Rock” or “R&B.” Rating “Rock” highly partially thwarts a rating of “Don’t Play” for “Classic Rock.” Furthermore, the system seems to prefer genre recommendations to song correlations, which is increasingly frustrating as you fine-tune your song ratings. Just as bad, if not worse, if you leave genres blank Yahoo assumes you like them all equally!
• One positive impact is that if you have a subgenre you’re interested in hearing more of, like “Big Band” or “Zydeco,” you can rank it heavily for a few days to get served a bigger sampling of songs so you can develop your opinion.
• Similarly, only rate an artist if you want them to impact the system’s choices. You might love Madonna or Depeche Mode, but if you aren’t interested in the terrible pop they’re correlated to you might be safer just rating songs and albums. Rating a smattering of songs by an artist has an equal (or better) effect on being served more songs by the same artist as rating the artist themselves.
• Whenever you hear a song you really like, click the song name to view its entry, which contains its similar songs. This is especially fun when listening to classic music that you don’t necessarily own, as it tends to jog your memory for other songs you’ve forgotten. (When you hear a song you really hate you should do the same thing; you might kill ten terrible-sounding birds with one well place stone. Or, you could find out a song you love is too closely correlated to the distasteful pick).
• There’s a fixed amount of time (or number of songs?) you can consume in any given month before higher features are locked out, leaving you only with your own station with a somewhat limited pool of songs. Our office seems to hit this point about 2/3 into a month. If your tastes run mainstream the limited pool is actually not so bad, but to avoid this make sure to shut (or at least pause) the player when you leave your desk.
• Though Yahoo’s awesome correlations per Artist, Album, or Song help support predictions of your taste, the system seems to be incapable of adapting to a non-standard correlative scheme on a per-user basis.

  For example, what if I rate “Don’t Play” on every song over five minutes? The system would learn to avoid long songs that were similar to each other, but voting no to Queen’s “Bohemian Rhapsody” and LedZep’s “Stairway to Heaven” wouldn’t necessarily protect me from Fiona’s “Never Is a Promise” or Tori’s “Yes, Anastasia.”

  A best-of-class predictive system would be able to determine your tastes not only based on correlated predictive data, but also based on your personal trend of ratings for certain song lengths, BPMs, producers, labels, or even mix levels and/or frequency response.

If you know of this promised land of music consumption, please point me in the right direction. Heaven forbid i learn enough programming/scripting to be dangerous, i might have a go at my own datamart, a la iTunes Registry.

I love music so much that i’m starting to think i need to hire a part-time “music-loving assistant” to help me love music as much as i love music.

My CD intake has become truly ludicrous over the course of the last month; since my latest acquisitions post i’ve purchased another 20+ discs, hardly any of which are bad. Yet, i hardly listen to 200 songs in my own collection a week – i average about 700 a month with iPod, and without (as i am, currently) i hover around 300. That means i’m not even listening to all of my new purchases once through iTunes.

My music loving issue is a symptom of something Coolfer was discussing earlier this week – namely, that the scarcest resource artists are vying for is not listeners’ dollars, but listener’s time. Because, an album that’s bought (out of loyalty, or advertising, or whatever) but not heard is like a tree falling in an empty forest: it might make a sound, but no one will know.

What Coolfer only begins to touch upon in their writeup is the world of music filtering tools that help the time-pressed listener discern what’s good, not only in their own collections, but in the vast realm of songs they haven’t heard.

To this point i’ve taken the recommendations of sites like Amazon or RateYourMusic with a grain of salt, often more suspicious than curious of an artist they correlate to my tastes. Plus, they’re only correlated on an album-by-album basis, when i truly operate on the song level.

To that end, lately i’ve become enamored with Yahoo’s LaunchPlayer customized station(at work only, as it doesn’t function in Firefox). In the player you can rate any level of music in a 5-point system – from the macro of Genres through Artists and Albums to the micro of Songs. Users rate via listening or, if you’re me, mass rating-drives to sync up to iTunes ratings (aside: why the fuck can’t i upload my ratings as CSV? Surely i can’t be the only person who worries about keeping ratings meticulously synced across multiple services?), and the customized stations spits out increasingly well-chosen songs (though it doesn’t plays only what you’ve rated, so rating every song by a certain artist improves its predictive abilities to find songs like those, but doesn’t mean you’ll hear more of those songs).

Even with about 2.5k ratings i’m obviously still in a calibration stage, as the player feels me out in various genres. It’s amusing how my current ratings (only synced through C in iTunes) are already yielding some of my favorite results from the rest of my music collection. However, it’s amazing how high the quality of recommendations become when the player gets on a streak; this week i was treated to a 5-song block of things completely new to me and completely excellent. Also, the player has a knack for reminding me of tracks i own but haven’t heard for years. If only i didn’t have to labor for hours on end to sync up its ratings to mine…

What i have a burning need to know is, why does this AWESOMELY PERFECT functionality need to be separated by my music collection by a brick wall of incompatibility and ratings mechanisms? The closest thing i can find as an iTunes plugin is LastFM (previously (or still?) AudioScrobbler), but the site is spotty in its tracking, can’t track my iPod usage, and doesn’t take into account my ratings (booooo). Since it can’t distinguish between a 5-Star Ani DiFranco track and a 1-Star Dave Matthews Band track, the service’s recommendations are nearly useless to me (i.e. I still manage to listen to a lot of things i don’t love, and it’s skewing my results mercilessly).

My great white hope was the iTunes Music Store “Just For You” beta feature – recommendations native to my music player! Except, they SUCK. iTMS doesn’t take your ratings (or any of your library) into account, just your purchases, and the only two distinctions it allows you to make are “Already Own It” or “Don’t Like It.” What about, “I bought it and it SUCKED!” or “Not my favorite album by that artist”? I need degrees, damnit.

I’m not sure of what my recourse is, short of a paying an assistant to make me daily playlists that combine old favorites with hitherto unearthed deep cuts and brand new singles. It seems to me like the majority of iPod users use iTunes, and a good deal of other music fans like it to, so i’m sure i’m not the only person hitting a wall in this regard.

What i’d love to know is: what’s in the pipeline? A Yahoo-like service that let’s music-head mass-upload their ratings and/or combines randomly streamed tracks with nuggets from your own library? Last.FM that also sucks in ratings and playcounts to become a better predictor (which can totally be done, as my NowPlaying sidebar is getting that same data live from iTunes as we speak). Or, an iTunes integrated monster that queues up iTMS songs as correlated to your Top 200 most played and/or highest rated?

Whatever the magic bullet is, i hope to get hit soon. Otherwise, the only thing standing between me and just listening to Immaculate Collection on repeat for days are iTunes’ Smart Playlists that mine my least-heard-but-highest-rated tracks.