And in a way that process is a very conducive way to listen to music that you haven't heard before. Just tune in and get on with your life. Soon you will hear a track you really like and think, I have to have this! On a site like Pandora or Last.FM, usually that means going out and buying the track. But since everything on Fresh Hot Radio is born on the Internet, free to download, you simply click on the link provided and get it. Mission accomplished.

We think Fresh Hot Radio hits its design goals perfectly. We've been listening to it for over an hour and the music has been great. If we want to keep a copy of the music, it's just a click away, and the site even has a URL and embed code for each track. We'd say it's the perfect accompaniment to our work day.

The user interface of the desktop player, which looks a bit like Mozilla's Songbird, is slightly more complex than it really needs to be, but it also gives you access to a set of powerful tools that go beyond the core recommendation service. The desktop player, for example, includes a CD burner and some rudimentary support for managing portable players. Thanks to its integration with AudioID, Mufin can also easily find MP3 id information for tracks in your collection that haven't been tagged with the right information yet.

Sort by Sound

At the center of the Mufin Player, is, of course, Mufin's recommendation engine, which allows you to quickly build playlists based on the music similarities between songs. Once you import a new song (Mufin can import your iTunes library, by the way), Mufin automatically analyzes the musical qualities of that song. Based on this, Mufin will then recommend similar songs from both your own collection, or based on information from Mufin.com, which currently features about 5 million tracks. Sadly, Mufin only allows you to play 30-second clips from songs it recommends from its own site.

The problem for Mufin, of course, is that most users already have a favorite music jukebox. Mufin's recommendation features are extremely interesting, and we recommend that you give it a try, but if you like Mufin's recommendations, then using the iTunes plugin might be more worthwhile for you in the long run.

mufin player from mufin on Vimeo.

Pandora: Humans Only

Pandora, one of the most popular music recommendation and discovery services on the Internet today, bases its recommendations on data from the Music Genome Project. The Music Genome Project assigns up to 400 attributes to every song. This, however, has to be done by trained musicians and the process can take up to half an hour per song. While the results of this method are often great, and we ourselves have often discovered interesting new music through Pandora, this approach simply doesn't scale very well and Pandora's library can often feel somewhat limited.

Mufin: Algorithms Only

Maybe the best known proponent of a music recommendations system that is purely based on algorithms is Mufin. Mufin's software analyzes the fundamental properties of a song and makes recommendations based solely on the musical similarity between songs.

While Mufin's approach generally works surprisingly well, the problem with this technique is that the system is simply oblivious to the cultural context of a song. Thanks to this approach, you might get to hear Christmas songs in February, for example, as the algorithms simply can't understand the cultural context of your music library.

At times, however, being agnostic to the cultural context of a song can also have its advantages, as Mufin's recommendations can often help you to rediscover music you had forgotten about. Mufin also works with any song, no matter whether it's from your own band, Kanye West, or an unsigned local band.

While Mufin's web service turned out to be a bit of a disappointment, we did like the company's iTunes plugin, which analyzes the songs in your library.

Lala: Explicit P2P Recommendations

Other services, like Lala, have decided to not feature any real recommendation technology at all. Instead, Lala purely relies on users following each other on the service and recommending new music to each other.

At least for Lala, this approach seems to work very well. When we talked to Lala's founder and CEO Bill Nguyen last week, he pointed out that 70% of all the music listened to on Lala was new music that was not already in a user's music locker, and that 18% of new music listened to on the service is bought and added to collections.

eMusic: Hybrid Approach

EMusic, the second largest online music store after iTunes, introduced a new recommendation system on its site late last year. This new system is based on technology from MediaUnbound, one of the larger providers of personalization and recommendation services. MediaUnbound, for example, provides the recommendations for MTV's Urge, Napster, and Brazil's Terra Sonora (eMusic, by the way, dropped Choicestream as its recommendation service in favor of MediaUnbound).

As MediaUnbound's CEO and co-founder Michael Papish explained to us last week, the company believes that a hybrid approach, which uses both algorithms and human input from experts, will provide the best results for users.

For eMusic, this means that the recommendations on the site are constantly fine-tuned by your own actions on the site, MediaUnbound's algorithms, and eMusic's editors, which, together with MediaUnbound's high-level teams, constantly evaluate the resulting sets of recommendations (Papish called this the "mosh pit" approach).

Genius: Apple's Black Box

It is hard to evaluate how Apple's Genius feature in iTunes really works, but Apple does have a few advantages. Because iTunes users often rate the songs in their library, Apple gets a lot of explicit information about a song's popularity. Users also regularly transmit information about how often they played and skipped a song to Apple's central servers.

Besides this, however, we can only speculate about what Apple looks at to give its recommendations. They surely evaluate playlists and the similarities between different users' libraries, for example. We can only assume that Apple uses a mashup of various recommendation techniques to come up with its own suggestions.

The results are generally quite good, though often either very predictable or completely random.

Opening the Black Box

In general, a black box approach similar to Apple's is still common for most recommendation services. Very few services give users a clear insight into why a certain song was recommended and the ability to fine-tune these selections (Pandora is a good example of a service that readily provides this kind of information). We are, however, seeing a trend towards users getting slightly more control over these recommendations. Slacker Radio, for example (see our review of their iPhone app here), lets users choose whether they want to hear more hits or more obscure artists on their radio stations. Mufin, too, gives users some control over how similar the recommended songs should be.

What Does Your Ideal Music Recommendation Engine Sound Like?

In general, we feel that every one of these approaches can provide us with relevant suggestions, depending on what kind of recommendation we are looking for. Of course, sometimes the easiest way to find great songs is to simply forget about the algorithms and editors and just look at what the people around you listen to on a service like imeem.

Do you have a favorite service for music recommendations? Or do you have some recommendations for these services that might help them to improve their service? Just let us know in the comments.

ReadWriteWeb Resources for Recommendation Technologies

We will be profiling other recommendation companies in upcoming posts. We also invite you to explore our custom ReadWriteWeb Resources:

• RWW Recommendation Industry Feed Favorites OPML file (save link)
• RWW Recommendation Industry Feeds - Best of Feed (copy and paste to your reader)
• Click to preview the above feeds before subscribing (pop-up window)
• RWW Recommendation Site Search (Visit and Bookmark)

CC-licensed logo image used courtesy of Flickr user shankar, shiv.

Overall, Slacker feels a lot like satellite radio, which is probably no surprise, given that XM Radio's co-founder Lon Levin is Slacker's Senior Advisor.

With regards to its user interface, every Pandora and Last.fm user will feel right at home. One nice addition to Slacker, though, is the ability to see which songs will play next.

Customization

One advantage of Slacker over its competitors is that it gives you more options to directly customize your stations. You can direct it to play songs from different decades, and decide if you want it to mostly play hits or also more obscure songs.

Competition

Slacker's reviews and biographies can't quite compete with the depth of information offered by the Last.fm app, which can also display tour dates. Slacker also doesn't feature any of the social networking functions that have made Last.fm so popular.

Just like its competitors, Slacker only allows you to skip six songs per station every hour. Unlike Pandora and Last.fm, however, Slacker does play 30 second radio ads after every fifth song. For $3.99 a month, however, you can buy a premium membership that lets you skip songs as often as you want and which removes the advertising from your stream.

Like all the other streaming music apps on the iPhone, Slacker can't play in the background while you surf the web or read your email. This, of course, is a limitation that Apple has put on its developers, even though Apple's own music player on the iPhone does this without causing any problems.

Verdict

Even though Slacker Radio is very similar to the Last.fm and Pandora app, we think it is definitely worth a try. Whether you prefer one over the other will depend on how happy you are with the music recommendations it gives and how important the social features of Last.fm are to you.

In our tests, Mufin often performed better than Apple's Genius feature, but for now, the plugin is only available for Windows.

Fingerprinting

Mufin creates a unique fingerprint for every song in your library when you start the plugin for the first time. You can choose if you want the recommendations to be based on the analysis of 30 second snippets (for fast analysis) or on the whole song (very slow, but highly accurate). Mufin's proprietary algorithms can then create playlists based on the similarities between the songs in your library. In creating these fingerprints, Mufin looks at over 40 characteristics, including tempo, instruments, and rhythm structure.

Apple's algorithms, on the other hand, are hidden in a black box, but seem to be based around the listening and purchasing habits of other users on iTunes.

Mufin's approach means that it will work for any song you may have imported into iTunes, no matter whether it is part of Apple's library or not. Mufin is also agnostic as to what language the songs are in.

Similar to Apple's Genius, the Mufin plugin will also make purchasing recommendations for similar songs that are not yet in your iTunes library and take you right to the iTunes store to listen to the preview or purchase them.

Verdict

Overall, we have come away very impressed with Mufin's recommendations. Judging from what we have seen so far, it may just replace the Genius feature as our preferred way of constructing automatic playlists.

That said, we are still not great fans of Mufin's core web service, which, unlike the plugin, is encumbered by licensing problems and which can only play 30 seconds of most songs (and often can't play the songs at all). The plugin, however, is a clear winner in our eyes.

The Top 10 tracks is absolutely dominated by Coldplay's Viva la Vida, with 6 songs - including numbers 1 and 2. The title track was number 1, with more than three million listens in about 6 months. Coldplay also features at 5, 6, 8 and 9. This is reminiscent of the dominance of the Billboard singles chart the Beatles enjoyed in April 1964!

The only other artist to make the top 10 tracks was Katy Perry at number 7 with 'I kissed a girl'.

Guess what's the number 1 album? Coldplay's Viva la Vida. Coldplay did have an impressive online launch for that much-anticipated album, which certainly helped. Indeed the album was also the biggest selling iTunes album download of 2008.

These charts, although depressingly dominated by a few bands, show that last.fm is a data generating machine. Its Scrobbler technology tracks what users listen to on a variety of media players - such as iTunes, Songbird, Hype Machine, Blip.fm. It tracks data at the rate of about 650 songs per second, from a community of over 25 million users worldwide according to the analytics firm Omniture. Last.fm claims this is the largest global database of online music behaviour.

Head of The Long Tail Wins Again

Last.fm says it currently has 43 million distinct pieces of music from more than 12 million artists in its database. Of course, even with such a 'long tail' of music data, clearly the Coldplays of this world will continue to dominate. It's not just Coldplay either, Radiohead probably would've been just as successful in 2007. According to one digger, last year "Radiohead would have been the entire top 10 tracks...". We can't verify that claim, but it sounds all too plausible given the 2008 data.

Although it's disappointing that mainstream artists can dominate charts even on the Internet, the beauty of online music services is that users can create their own Top 10's too. Thousands of those won't include Coldplay (including this author's!).

The complete "Best of 2008" lists from last.fm:

Best Artist (artists who have released their debut album this year)

1. MGMT - Oracular Spectacular

2. The Ting Tings - We Started Nothing

3. Sara Bareilles - Little Voice

4. Fleet Foxes - Fleet Foxes

5. Katy Perry - One Of The Boys

6. The Last Shadow Puppets - The Age of the Understatement

7. Foals - Antidotes

8. Bon Iver - For Emma, Forever Ago

9. Does It Offend You, Yeah? - You Have No Idea What You're Getting Yourself Into

10. Santogold - Santogold

Best Album

1. Coldplay - Viva la Vida or Death and All His Friends

2. MGMT - Oracular Spectacular

3. Portishead - Third

4. Nine Inch Nails - Ghosts I-IV

5. The Ting Tings - We Started Nothing

6. The Kooks - Konk

7. Death Cab for Cutie - Narrow Stairs

8. Hot Chip - Made In The Dark

9. Jack Johnson - Sleep Through The Static

10. Sigur Rós - Með suð í eyrum við spilum endalaust

Best Track

1. Coldplay - Viva La Vida

2. Coldplay - Violet Hill

3. MGMT - Time To Pretend

4. MGMT - Electric Feel

5. Coldplay - Life In Technicolour

6. Coldplay - Cemeteries of London

7. Katy Perry - I Kissed A Girl

8. Coldplay - 42

9. Coldplay - Strawberry Swing

10. MGMT - Kids

The free version of Songbeat allows you to download up to 25 songs for free, but in order to download an unlimited number of songs, users will have to pay $29.99.

Features

Of course, there are already numerous application (online and offline) that allow users to search and play songs from various free music services. Some of the features that make Songbeat stand out are the ability to quickly import your downloaded songs to iTunes, Winamp, or the Windows Media Player, as well as its large directory of mixtapes. Songbeat also automatically downloads lyrics and album art with every song.

Money

Besides selling the full version of Songbeat, the company hopes to make money through the 'Songbeat Discover' service, which allows users to legally buy songs from Amazon's music store and concert tickets from Ticketmaster.

Legal?

There are some obvious legal questions about the service. Songbeat's founders Philip Eggersgluess and Marco Rydmann argue that Songbeat only creates a model for monetizing music that is already freely available online. However, it remains to be seen if the RIAA will agree with this line of reasoning.

In our tests, Mufin often performed better than Apple's Genius feature, but for now, the plugin is only available for Windows.

Mufin creates a unique fingerprint for every song in your library when you start the plugin for the first time. You can choose if you want the recommendations to be based on the analysis of 30 second snippets (for fast analysis) or on the whole song (very slow, but highly accurate). Mufin's proprietary algorithms can then create playlists based on the similarities between the songs in your library. In creating these fingerprints, Mufin looks at over 40 characteristics, including tempo, instruments, and rhythm structure.

Apple's algorithms, on the other hand, are hidden in a black box, but seem to be based around the listening and purchasing habits of other users on iTunes.

Mufin's approach means that it will work for any song you may have imported into iTunes, no matter whether it is part of Apple's library or not. Mufin is also agnostic as to what language the songs are in.

Similar to Apple's Genius, the Mufin plugin will also make purchasing recommendations for similar songs that are not yet in your iTunes library and take you right to the iTunes store to listen to the preview or purchase them.

Verdict

Overall, we have come away very impressed with Mufin's recommendations. Judging from what we have seen so far, it may just replace the Genius feature as our preferred way of constructing automatic playlists.

That said, we are still not great fans of Mufin's core web service, which, unlike the plugin, is encumbered by licensing problems and which can only play 30 seconds of most songs (and often it can't play the songs at all). The plugin, however, is a clear winner in our eyes.

Sponsored Lyrics Pages?

Interestingly, Last.fm also announced that it will allow sponsors to advertise on these lyrics pages, including the ability to skin the entire page. We cannot help but wonder if this is a prelude to similar advertising options on other parts of Last.fm's site.

800,000 Lyrics

Even though 800,000 is a large number, this still leaves the majority of Last.fm's catalog without lyrics. The music industry has always been highly protective about lyrics and has been playing a cat-and-mouse game with many of the independent (and often user generated) lyrics sites.

LyricFind, too, started as a rogue lyrics site in 2000, but has licensed content from over 1,700 music publishers since then, including EMI, Sony, and Universal BMG.

Overall, adding lyrics to song pages is a smart move by Last.fm, as it turns Last.fm into even more of a one-stop music experience and also gives the service yet another feature that sets it apart from other music recommendation and discovery sites.

Mufin.com, however, which launched today, uses a fully automated system that only takes the actual sounds of a song into consideration. In our tests, Mufin often returned good results, but the fact that it doesn't take genres or the quality of a song into account can make for a frustrating experience at times.

Eclectic Recommendations

There is something to be said for this completely algorithmic approach. While social recommendation services tend to return results that safely stay within the same genre as the original song, Mufin's choices are far more eclectic. The most closely related song to Rick Astley's seminal "Never Gonna Give You Up," for example, is a song in Bavarian by a German folk pop group. Mufin really seems to like German songs, by the way, as more than half of the songs it recommended as similar to Frank Zappa's "Muffin Man" were from a Sesame Street album in German. In Mufin's defense, though, all these songs were quite similar in style to the original song.

Social Recommendations vs. Algorithms

As MG Siegler points out, the real advantage of social recommendation engines is that they are very good at filtering out bad music (though one might also argue that this can lead to slightly boring recommendations at times). Mufin neither cares about the quality of the music nor its popularity or language; it only looks at characteristics like tempo, instruments, sound density, and harmony.

Limitations

Mufin has already built an extensive library of songs, but it only holds the right to a limited set of them, which means that you simply can't play a lot of the recommended songs. Those songs that can be played are limited to 30-second previews , which can make it hard to decide if a song is really good and similar enough to warrant buying it.

If Mufin had partnered with a service like Rhapsody, for example, users would at least have been able to stream a limited number of full songs every month. Every song on Mufin features a link to iTunes and the Amazon music store.

Overall, we think Mufin is an interesting experiment, but we are not convinced that its algorithms return better recommendations than the more social approach of its competitors or the classification system of the Music Genome Project that drives Pandora's recommendation engine.