Category Archives: Online Shopping

A classically trained search engine

Image source: http://www.flickr.com/photos/jazbeck/

No, Amazon, when I say “Beethoven’s 2nd” I am not looking for a kids film about a freaking St Bernard.

As most of us who have ever tried it will know, searching for classical music online is a hit-and-miss affair.  There’s a reason for this.  Most search engines decide which results are relevant to you by matching words in your search query with words that appear in a particular web page, document or record.  The more words matched within a given document, the more ‘relevant’ a search engine believes it to be and the higher up the list of search results it will go.

The problem with this type of search is that it is fundamentally ‘dumb’. The search engine has no built-in understanding of the words you use in your search query.  It doesn’t know that a “piano concerto” is a musical form, that “Mozart” is a composer, that “A major” is a key signature, and that the “A major piano concerto by Mozart” is not the same thing as “a major piano concerto by Mozart”.

This is not terribly surprising.  Most search engines have no idea who you are, or what you are going to type into them.  In the US last year, the top ten Google searches included “Boston marathon”, “government shutdown”, “VMAs”, “new pope” and “Mayweather vs Canelo”.  That’s a pretty diverse range of topics, and no search engine could be expected to have an intelligent understanding of each of them.

The problem is worsened quite substantially when numbers are introduced into a query. This is pretty much impossible to avoid with classical music, whether you’re looking for “beethoven piano concerto 5“, “schoenberg 5 pieces for orchestra” or “corelli’s 12 violin sonatas op 5“.  Because a search engine doesn’t really understand the terms you type into it, it cannot deduce from the context what sort of number you’re looking for.  Instead, it just searches for matching numbers within its database.

The result is that a search for “beethoven symphony no 5” might yield an album of (say) Beethoven‘s Symphony No. 7 coupled with the Piano Concerto No. 5.  From the search engine’s perspective, that’s not a bad match.  From yours, it could definitely be bettered.

This inability to intelligently comprehend what you are looking for is why traditional search engines don’t really work for classical.  Completely unambiguous search terms such as the following yield completely different sets of results, even on the two biggest online music retailers:

 

 

Search Results

 

Good luck guessing which of those results sets has the particular recording you’re looking for in it!

Solving this problem has been one of Lelio’s key aims over the last 18 months.  Our search engine was built with classical music in mind from the very beginning.  We were able to do this because, unlike a traditional search engine, we know what type of information our users are likely to be looking for.  It is then just a matter of programming the search engine to intelligently interpret queries about that information.

So for instance, when you type “beethoven symphony 3″ into the Lelio search box, it understands that Beethoven is a composer, a symphony is a musical form, and 3 (in this context) probably refers to a particular instance of that musical form.  If you typed in “beethoven symphony 55″, however, it knows that there is no 55th symphony and instead checks to see whether there is a matching symphony under Op. 55 – which, in this case, there is.

Key to the efficacy of this model is ensuring that every term in our database is unique.  It’s no good having different records for “Tchaikovsky”, “Tschaikowski” and “Tchaik” (as his mates call him), when they are all synonyms for the same composer.  Likewise, Lelio will accept any of the following variants of the word “symphony”:

  • symphony
  • sinfonie
  • symphonie
  • sinfonia
  • sin
  • sinf
  • sym
  • symph

As far as Lelio’s search is concerned, all of these terms mean the same thing (and in the next release, it will also recognise misspelled variants just in case you have chubby fingers like me.) This is what allows us to return such a consistent set of results.

Why is this consistency so important, you ask?  Well, remember how the other week I blogged about Lelio’s mission to revive classical music sales?  Well, it turns out that in the world of sales, positioning is everything.  Just look at this graph showing the clickthrough rate of Google’s search results:

Optify analysis of Google top 20 search results click-through rate

What this graph demonstrates is that someone is almost three times as likely to click on the first search result they get offered than on the second – and over 16 times more likely than on the tenth.  If someone wants to buy something, it pays to ensure you’ve positioned it smack in the middle of their sight line.

With Lelio, we take things one step further. If our search engine considers your search to be wholly unambiguous, we don’t even display a list of search results: we just take you straight to the item you’re looking for.  At the moment, this is limited to composers or works, but artists and recordings will be coming in the next release.  The idea is to save you valuable time which can be better spent deciding whether you want the Furtwängler recording or the Klemperer.  (Top tip: get both!)

At any rate, we think this technology works really well and removes a big degree of randomness from the process of searching for classical music.  As I said in my last post, however, we know our prototype search engine is extremely limited – but we hope you enjoy playing around with it anyway and seeing what it could be capable of in the future.  If you have any feedback, we’d love to hear it – and please do share this blog using the buttons at the top of the post if you like what we’re doing.

Solving classical music in the 21st Century

Shopping for classical music in the good old days

In my last post I discussed the disheartening decline in classical sales over the last couple of decades.  From representing 11% of the recorded music market back in 1990, classical has dropped to just 3% today.  The collapse of traditional bricks-and-mortar record shops has forced classical customers online, where we are treated very much as second-class citizens in a retail landscape thoroughly dominated by pop music.  Inadequate technology means that finding the specific album or recording we want to buy has become a hit-and-miss affair, usually involving our having to wade through countless irrelevant search results before we (maybe) find what we’re looking for.  Many of us just give up, creating a vicious cycle whereby dwindling classical sales disincentive online retailers from investing in the genre and fixing the situation.

Something desperately needs to change.  And that’s where Lelio comes in.

When we started working on Lelio back in 2012, we had a fairly straightforward aim: to make classical music as easy to buy online as it is in a shop.  That might sound simple, but there are several big challenges that we’ve needed to overcome.

To start with, it’s worth pointing out that online shopping does have some natural advantages to the traditional “walk into a shop and buy what you want” experience.  For a start, there’s no walking involved (which is a major plus in my books).  Online shops can also carry a much bigger range of stock than their offline counterparts.  That means more choice for the customer, which in theory is a very good thing.

In the world of classical, however, the sheer size of that range can be daunting.  There are over 150 commercially available recordings of Beethoven’s Ninth Symphony alone, with more being released every year.  For someone just beginning to build their classical collection, knowing where to start is tricky.  For a more experienced collector, knowing where to go to next can be just as much of a challenge.

This is where a traditional shop has the advantage: any classical section worth its salt will have a chap behind the counter who can help you find a recording to suit your needs.  Failing that, there’s always the ubiquitous (and usually thoroughly dishevelled) copy of a Penguin Guide or Gramophone Guide lying around on the counter.  Online shops might be able to offer you customer reviews and star ratings, but they are no substitute for an expert opinion.

But even if you did just want to wing it, in a traditional shop you at least have the option of browsing through all the available recordings yourself.  That’s because in an old school classical section, albums are handily organised by composer and composition, rather than sales rank or release date.  This style of organisation – an A-Z listing of composers, with each composer’s works neatly filed under Symphonies, Concertos, String Quartets, Piano Sonatas etc – works brilliantly for classical shoppers, but is entirely absent from the online shopping experience.

So, Lelio’s first challenge has been this: how do you create a structure for selling music which is appropriate to classical?  Most online retailers simply take the view that copying and pasting the dominant “songs and albums” model will be sufficient for us classical customers.  With Lelio, we’ve thrown away that model completely, and started again from scratch.

I don’t want to bore you with in-depth discussions about our database design, but suffice to say that every album on Lelio is defined in terms of which compositions it contains.  This is in fact a radical departure from an album being defined in terms of artist name and album title, which is the model used by pop music and the model into which classical music is shoehorned by every record label and online retailer out there.

Building our database using compositions as the basic building block allows us to do a lot of really neat things.  We can group all recordings of a particular composition together under a single set of results.  We can group compositions together by composer, and build categories and hierarchies for that composer (e.g. Chamber Music –> String Quartets –> Late String Quartets).  We can slice and dice our data to show you all Bruckner recordings by Daniel Barenboim, then let you pivot to see all of Barenboim’s recordings of the Beethoven piano sonatas, and let you pivot again to see the Beethoven sonatas recorded by András Schiff.  We can also do some really, really neat tricks with our search engine, but I’ll discuss that in another post.

Ultimately, our hope is that by starting from the position of loving and understanding classical music, we can build something that really resonates with classical fans.  We want customers to have a nice time shopping for music, rather than pulling their hair out over the inadequacies of the technology.  By rebuilding the online shopping experience from the ground up, our hope is nothing short of revitalising the classical sector – replacing the vicious circle I mentioned earlier with a virtuous one.

All of this is a huge undertaking, though, and we can’t do it all at once.  Next week I’ll talk about our more immediate goals, why our current prototype website only has 150 recordings listed on it, and when you can expect to see the next round of developments.

In the meantime, if you liked this blog, you’ll be doing us a big favour by sharing it on Facebook or Twitter!

Lelio: The Prehistory

Somewhere in this primordial soup you can hear Lelio being born

It’s been a little while since I’ve updated this blog, for which I must apologise.  Keeping a blog is a little like keeping a pot plant: without regular attention and nourishment, it will wither and die.  I was never much good at keeping pot plants, and I fear that as far as the Lelio blog is concerned, the brown leaves have long started outnumbering the green ones.

But it’s a new year, which means that it’s as good a time as any to turn over a new leaf (if you’ll forgive me overextending the plant analogy).  I’m going to be updating this blog much more regularly from now on, so watch this space.  I’m also going to be moving away from general ruminations on the world of classical music – there are plenty of other talented bloggers covering those subjects as it is – and talk to you instead more about what Lelio is all about, what we’re working on, and why we’re doing what we’re doing.

I’m going to start with that last point, which entails a short, slightly depressing history lesson.  Sorry.  There will be gleaming futuristic awesomeness in the next post, possible featuring hovercars and world peace.  Promise.  In the meantime. . .

The Problem with Classical Music (Abridged Version)

Back in the early 1990s classical music was a pretty big deal. Globally, one dollar in every ten spent on recorded music was spent on classical.  This was partly fuelled by the introduction of the compact disc in the mid-80s, a format which represented a significant improvement over the cassette tapes of the preceding generation, and whose introduction precipitated a spate of re-buying amongst audiophile collectors.  Classical fans led the charge in this department, and small wonder: the CD had been developed with classical interests firmly in mind, to the extent that the actual physical dimensions of the new format had been defined as ‘just big enough to fit a complete recording of Beethoven’s Ninth Symphony on a single disc’.

By the turn of the century however there was a new game in town, and it was called the MP3.  Far easier to buy and much more portable than CDs, the MP3 – along with its less famous but more widespread cousin the AAC – promised to change the record industry forever.  Apple released its iPod in 2001, and in just under a decade transformed from a slightly unloved technology company into the world’s single largest music retailer – all because it was first to ride the new wave of downloadable music.

What a pity, then, that downloads represented such a backwards step for classical fans.  Highly compressed audio was never going to unseat CD in the sound quality stakes, and the portability benefits downloads offered was only of limited interest to the three-quarters of us who still do most of our listening at home.  The only possible advantage a download could offer over a CD was the convenience with which it could be bought: online, from the comfort of one’s own home.

But even the convenience of buying music online had been compromised when it came to classical.  Just finding classical music was – and continues to be – a huge pain in the proverbial.

Type in the name of a Beatles album, and iTunes or Amazon will be able to point you to it, take your money and deliver your music to you before you can say “it’s not actually called The White Album officially you know”.

If, on the other hand, you are looking for a specific recording of Tchaikovsky’s Pathétique Symphony, you and the retailer first need to agree on the correct spelling of Tchaikovsky (Tchaikovsky? Tschaikowsky? Tchaïkovski?), whether you wanted the “Symphony 6” or the apparently unrelated “Pathetique Symphony“, whether you meant the “VPO” or the “Wiener Philharmoniker “, and finally sort out who this Rafael Kubelik fellow is anyway.  It’s a mess of shoddy data, inadequate search tools, and an apathetic attitude by retailers that reflects the decreasing importance of classical buyers.

Shopping for classical music online has become a confusing and frustrating experience, and without any pressing need to upgrade our CD collections, it has become less and less worth our while to get out our credit cards.  The result?  Classical has dropped from 11% of worldwide music sales to just 3%.

Worse, this decline has become self-perpetuating:

Classical cycle

 

The only way to halt the decline of classical music is by breaking this vicious cycle.  And that’s where Lelio comes in.  My collaborators and I have invested over 18 months of our lives into this so-called ‘dying genre’ because we believe that there remains a strong, committed audience for classical music out there.  We want to make shopping online as enjoyable and engaging an experience as nosing around in the classical section of your local record shop used to be.  Ultimately, we want people to buy more classical music.  And we want to do that because we want to see classical resurge and grow strong once again.

In the next post I’m going to talk a bit more about how we’re actually hoping to achieve all this – and how you can help.  In the meantime, I wish you all a very happy New Year and promise – cross my heart and hope to die – not to let this blog shrivel up again.

Lost in translation

The former president of EMI Classics once told me that classical music had a natural advantage over other forms of music: since a lot of it is instrumental, it travels extremely well.  There are no language barriers.  Beethoven’s Fifth Symphony is just as comprehensible in São Paolo or Kyoto or Reykjavik as it is in Vienna, where it was composed.

Putting aside obvious exceptions such as opera for a moment, I tend to agree with this idea.  Classical music is the most abstract of all the arts.  Literature, fine art, theatre, dance and film all started out as essentially representational art forms.  Music has always appealed to some other, less literal part of our brains.

So the task of having to describe it in literal terms is somewhat antithetical to its nature.  For most of classical music’s existence, composers have rebelled against the notion of ascribing concrete meaning to their music.  That’s the reason a work as elementally powerful as Beethoven’s Fifth is known by its form, Symphony, and its number, 5, rather than by some reductive nickname such as “Fate” or “On Deafness” or “The Napoleonic Wars Really Suck“.

However, that essentially abstract nature doesn’t help us much when we’re trying to find music, because the way we communicate – with search engines, just as with one another – is through the medium of verbal language.  With search engines we don’t even have the advantage of being able to ask them what the name of that piece that goes “da-da-da-daaa” is – at least not yet!

So we’re stuck with written language, and that’s where things start go awry.  The other day, a friend told me I should check out Jos van Immerseel’s recording of Rimsky-Korsakov’s Scheherazade.  So this morning on my way home from the gym, I thought I’d try and find it on Spotify and give it a listen.

I was looking for it on my iPhone, which gives me the option of searching Tracks, Albums or Artists.  As I wanted to listen to the whole album, I searched under Albums.  No results.  What a shame, thought I.  But then it occurred that perhaps I should look under Tracks.  Still no results, but this time a suggestion: “Did you mean immerseel sheherazade?

I had to look closely at my screen to see how that differed from what I’d asked for.  When I tapped the suggestion it brought up the following set of tracks:

  • Shéhérazade, Op. 35: La mer et…
  • Shéhérazade, Op. 35: Le réci…
  • Shéhérazade, Op. 35: Le jeune…
  • Shéhérazade, Op. 35: La fête à…

etc.

It was clearly a French release of the album that had been left untranslated for an English-speaking audience.  The problem with this is that Shéhérazade is, to the English-speaking world, a completely different piece by Ravel, a set of orchestral songs not to be confused with the symphonic suite by Rimsky-Korsakov.

It didn’t help that Spotify’s iPhone app had also handily removed Jos van Immerseel’s name from the metadata.  Instead, underneath each track was the mysterious term “Anima Eterna“.  In other words, if I hadn’t known the opus number of Rimsky-Korsakov’s piece and the fact that Jos van Immerseel’s orchestra is named Anima Eterna, I’d have had absolutely no idea that I’d actually found what I was looking for.

This is a classic example of how badly classical music suffers from shoddy metadata.  In Lelio‘s master database, we have a way around this: every piece of data is multilingual.  We don’t have Scheherazade in there yet, but try searching for something like “Die Geschöpfe des Prometheus”.  You should get The Creatures of Prometheus Overture by Beethoven.  Once we turn on multilingual support, German speakers will be able to do this in reverse.

In the meantime, do check out Immerseel’s Scheherazade or Shéhérazade or, as Rimsky himself would have known it, Шехерезада.  It’s worth waging battle with a search engine for.

Why online music stores are failing classical

All the way back in October 2007, I penned a little rant for The Guardian entitled iTunes is clueless when it comes to classical music.  I was fairly new to the world of digital music in those days, but even then it was clear that online music stores weren’t really working for classical music.  My particular gripe in that instance was that there was no way for me to download an individual work – in this case Vivaldi’s Gloria, consisting of a dozen movements – without shelling out for the whole album.

It was a small issue, but it illustrated an important underlying problem: classical music was a poor fit for the ‘songs’ and ‘albums’ model being used by online music retailers.

Given five years is the equivalent of about three millennia in the technology world, you would expect things to have moved on since I wrote that piece.  And indeed they have.  iTunes now acknowledges the concept of multi-part compositions, offering them as complete works you can buy as discrete bundles.  They’ve addressed a number of other complaints from classical fans, too, such as improving sound quality.

But there is still a long way to go.

For a start, searching for classical compositions is still a hit-and-miss affair at best.  A few months ago, I tested both iTunes and Amazon to see how they handled a variety of search terms one might use to find recordings of Beethoven’s 3rd Symphony.  Just look at the huge variance in the number of results:

Search Results

Every one of those search terms unambiguously points to a single piece of music – and yet the two biggest online record shops will give you a wildly varying set of results depending on the exact set of words you choose.

It would be very easy to blame the retailers themselves for this.  But the problem is more pervasive then that, and in fact affects even the big specialist classical record labels.  The problem is metadata.

Metadata, for the uninitiated, is data that describes other data.  In this case, it’s the text that describe what you’re listening to.  For most pop records, this is pretty straightforward stuff: Artist and Song Title are usually sufficient to find pretty much anything in the popular music back catalogue.

But who is the Artist on a piano concerto?  Or an opera?  Is it the composer?  The soloist?  The singers?  The conductor?  I’ll bet everyone reading this has had the experience of finding the Artist field taken up exclusively with the name of the composer, and thus having absolutely no idea who the actual performers are.  Matters are made worse by the fact that many classical performances are a collaboration between several artists: ‘Herbert von Karajan & the Berliner Philharmoniker’ is not in fact the name of a 60s garage band, but rather two separate entities unhelpfully crammed into a single metadata field.

Worse yet is the problem of Track Name.  This is particularly problematic because most classical compositions don’t even have proper names.  Generally, we know them just by a set of parameters.  Going back to the example of Beethoven’s 3rd Symphony, for instance, you could describe it like this:

  • Musical Form: Symphony
  • Musical Form Instance: No. 3
  • Key Signature: E-flat major
  • Catalogue Number: Op. 55
  • Nickname: “Eroica”

You can pretty much assemble those parameters any which way you like to describe the piece in question.  And indeed that’s just what record companies do, squeezing all that data down into a single field called ‘Track Name’.  Because nobody condenses their data in exactly the same way, this leads to enormous inconsistency between record labels, which in turn leads to inconsistent search results.

Of course, it’s hardly surprising record labels and online retailers haven’t felt inclined to build a completely new metadata standard for classics.  Classical music accounts for just over 3% of total record sales worldwide.  It’s simply not worth the investment.

This is where Lelio is different.  We’ve built an entirely new standard for classical music, and paired it with a brand new type of search engine that ‘gets’ how classics work.  Our aim is simple: we want to make classical music easier to find, easier to buy, easier to compare and easier to enjoy.

I’ll be blogging in more detail about how we’ve gone about addressing the problems described above, as well as how Lelio plans to thwart a number of other bugbears that have plagued classical fans since the dawn of the digital revolution.

In the meantime, let us know what you think.  Do you share these frustrations?  Do you think things have got better over the years?  Or worse?  How would you rate the online experience versus the good old bricks-and-mortars approach?  Is there anything you prefer about it?  Or do you long for the days where a record meant something made of vinyl that you could hold in your hand, rather than just another entry in a database?