Wine recommenders, and the tyranny of choice

Half a century ago, a man named Alvin Toffler published a book called Future Shock (1970). This was a big thing in my youth, and it set the scene (and the tone) for much of what has happened in human societies since then. You see, the book was about the way in which the world had dramatically changed since the end of World War II, and what the effects of this might be on cultures worldwide.

One of the fundamental tenets of the book was about the increasing number of choices that we all face. Back in the Old Days, most people had relatively few choices in their lifetime, because they lived in a geographically and economically restricted world. The more restricted your life, then the fewer choices you actually have — most things happen to you, rather than you choosing them.

Well, the various cultural revolutions that started in the second half of last century put paid to all of that, except in the poorest communities. We now face a myriad of choices every day; and Toffler could see the possibility of this becoming overwhelming, at a personal level. After all, we have no inbuilt mechanisms for making choices rationally, and no cultural background (at that time) that could aid us. This had never happened before in history; and it has become know as The Paradox of Choice (freedom of choice is Good, but enforced choices can be Bad).

This led to the issue that Toffler focussed on in his book: "information overload" — when change happens fast, it results in social confusion and the break-down of prior decision-making processes. How do we make choices in a world that keeps creating more and more choices for us? These choices range from life-changing decisions, all the way down to daily preferences. But the "shock" of the future is that the number of choices to be made will not decrease, simply because our societies are changing at a rapidly increasing rate.

The wine industry

So, what has all of this to do with wine? Well, wine provides one really practical example of a (presumably less than life-changing) set of choices. In my lifetime, the choices for wine consumption have fulfilled Toffler's vision perfectly. I don't, as my forebears did, drink local wine, beer or spirits, depending on what plants could be cultivated in the local climate. I can get wine from anywhere on the planet, due to revolutions in transportation, and I can afford an awful lot of it, due to economic and social revolutions.

How do I make my choices? This is actually a pretty important question, not just for me personally, but for the wine industry as a whole. How are customers going to make decisions, when faced with potentially over-whelming choice, especially at the retail-shop Great Wall of Wine? What are the best ways for them to do so, and how do we help them do it? It would be a serious failure of the industry not to address these issues, sooner rather than later.

This is not an issue unique to the wine industry, of course. All industries currently face it, from vehicle manufacture, to an increasing number of media types (music, movies, TV), to holiday destinations. However, the biggest difference is the sheer number of products involved in the wine industry, compared to any other industry; and we make it worse by insisting that each single vintage is different (Vivino reports 13 million distinct wines in its database!).

To me, the ultimate outcome of failed recommendations is not so much that customers might make a wrong choice, but instead they make an arbitrary choice, which may then (for them) turn out to be right or wrong in some unpredictable way. The only alternative is for them to stick to the same old choice that they made last time, thus effectively ignoring all other choices. Moreover, this choice will be relatively inexpensive, so that the financial consequences of the choice do not particularly matter. This is no way to run a business.

Recommendation systems

The Information Revolution is supposed to be able to help us with this situation. The key concept is to create what is called an "information filtering system". Choices are addressed by eliminating all of the unsuitable ones, for any given customer. The customer can then make a much easier choice from a much smaller subset of possibilities, with some degree of confidence that this will not result in a wrong choice.

So, various industries have tried to tackle the issue in a computer-based manner, with varying degrees of success. I don't intend going into detail here, as there are plenty of articles on the web for you to read (start with Recommender system, at Wikipedia). However, all of the recommendation systems employ one or more of the following generic types of approaches:

• aggregated reviews from previous customers (eg. Amazon, TripAdvisor, Yelp, CellarTracker, Vivino)
• aggregated reviews from alleged experts (eg. Rotten Tomatoes, Wine-Searcher)
• club membership with standardized products (eg. Winc, Tasting Room)
• content-based filtering, which matches customer preferences to product characteristics (eg. Pandora, Wine Genius, Sippd, Bright Cellars, Vivino)
• collaborative filtering, which matches customer preferences to the preferences of other customers (eg. Netflix, Vivino)
• recommendations from one or more commentators whom we personally trust to have a taste something like our own (not really a computer-based system, but these days all of the commentators have social media presences).

When comparing these options, I personally like the last one best, when it works, as it represents the Old School way of doing things. The problem, however, is that there are too many such commentators, and most of them write about wines that I do not have access to (and some of the critics rely too much on ratings rather than reviews). So, this antiquated approach can be very effective in practice, but the customer has to put in a lot of time and effort. It is unlikely that young people are going to become wine customers if this is all we have to offer.

Of the other alternatives, I personally find customer ratings/reviews mostly worthless. A 5-star review tells me nothing more than that the person had a good experience, and a 1- or 2-star review says the opposite — I usually get no idea from the reviews why either person reacted the way they did. I therefore have to wade through the 3- and 4-star reviews, looking for some useful information. Amazon has stuck to this idea, but Netflix abandoned it.

Moving to the next option, one essential problem with content-based filtering is the nature of the content. That is, what characteristics do we measure about the product, and how do we describe them to the customer, in order to link the two? There have been some very ambitious attempts at this, such as the Music Genome Project for the Pandora music recommender. Sadly, such systems are often “data-rich but information-poor”, which is a well-known aphorism in the data industry (see my blog post: The Music Genome Project is no such thing).

Another issue is how the computer should actually link the products and customers. Artificial intelligence (AI) is becoming a common technological option (Old world, new tech: how the wine industry is taking on AI). The ideas behind AI, as currently applied to wine, have recently been discussed by the Wine Curmudgeon (“Curated” wine clubs, and why they don’t seem to be the answer). He has also previously had a go at standardized products from wine clubs (Blue Apron wine: disappointing and depressing) (see also: Are wine clubs worth joining?, and the recent Life under lockdown prompts wine club revival).

That leaves one final option, for which AI could also be used. In an ongoing series of articles, Lewis Purdue is currently discussing collaborative filtering, very positively (and critiquing most of the alternative methods):

1. How a Netflix-style recommender is vital to reversing wine’s market marginalization
2. Why solving the “Paradox of Choice” is a major reason Netflix’s recommender is worth $1 Bil/yr.; and why wine fails at that
3. Reviews and 5-Star are so useless for recommendations that Netflix tossed its prized $1-million algorithm; they’re even worse for wine
4. Wine wreck-commendations: Genes determine that no two people taste the same wine the same way
5. Netflix amped up recommendations with its own Big Data. What that means for wine
   
6. A “Netflix of wine” is impossible with current recommendation methods because Sight & Sound dominate Smell & Taste
7. Capturing individual perceptions of wine is the path to Netflix-quality recommendations

An example

This is not to say that people in the wine industry are not trying to create useful recommendation systems. However, I am not convinced that anyone has succeeded yet. We can look at the example provided by Vivino, which you will notice was listed several times above.

This system started in 2010, when a couple of Danes, who admitted to knowing very little about wine, decided to create a visual wine information system, on the basis that most people process information much better pictorially, rather than via text.

So, they took the basic model used by CellarTracker, which was originally almost entirely text-based, and then allowed people to access the wine data via pictures of bottle labels (using the Vuforia image-recognition engine). This worked, so they created an app, because in the modern world people access information using a mobile device — this is apparently now the most downloaded mobile wine app (see also: Wine: the trouble with wine apps).

They then decided to monetize the system, by allowing people to purchase wine through the app, via retail partnerships (Selling through Vivino - how's it working for you?). To do this, they basically adopted a content-based filtering procedure, in which customer preferences (based on their use of the app) are matched to similar products. That is, if you show an interest in a certain type of wine, then the app will direct you to allegedly similar wines.

More recently, they have moved towards a more collaborative filtering system, which matches customer preferences to other customers with apparently similar preferences. So, if some other customer is allegedly similar to yourself (based on their use of the app), and they like a particular wine that you have not yet tried, then the app will suggest that you might like it, too. Netflix has had great success with this approach to recommending movies.

We shall see how Vivino progresses (ie., is their current model going to work?); but you can see that they are at least trying.

The bottom line

The purpose of this (long, non-data) post is to emphasize the importance of the basic point. The contemporary wine industry confronts potential customers with a scale of choice almost unparalleled in the commercial world; and it currently does so with very little in the way of assistance for those customers. This is not a viable business strategy. The wine industry currently focuses on producing wine and on selling wine; but it does not (yet) fully address customer service in the Information Age.

In this sense, the wine industry is a hang-over from the Good Old Days. Back then, customer service was all about a person walking into a shop and being served individually by another human being, who may or may not succeed in helping that customer. This was inefficient, even back then, because it relies on the customer making the first (big) move.

Well, those days are rapidly going; and the current pandemic has accelerated the departure. I'm an old guy, and I miss being able to browse in shops; but it is too risky for me to do it just now, precisely because I'm an old guy. This issue is actually encapsulated in another idea from Alvin Toffler, noting that the personal touch is often the key, rather than a focus on information. After all, we are humans, not just information processors. Toffler said:

Society needs all kinds of skills that are not just cognitive; they're emotional, they're affectional. You can't run the society on data and computers alone.

The wine industry has always relied on this personal approach. However, it cannot work well in the face of information overload, particularly not the sort currently being perpetrated in the wine industry. We thus face our own choice regarding potential customers: start providing effective help with making choices, or drastically reduce the number of choices. Less really is more.

Terroir and global warming

When I first started to learn about wine, many French wines commanded a price premium, and were apparently intended as an aspirational connoisseur drink. This, at least, was the idea presented by the (mostly British) commentators of the time. New World wine was seen as much more down-market, as it was not quite so much tied up with the notion of "terroir".

Terroir is a complex issue, and it has thus been the mainstay of wine writers for many decades. The experts obviously understand terroir, and the rest of us apparently do not (at least, until we have read their words on the subject).* Like many people, I suspect that this idea is becoming more and more problematic this century. Shouldn't global climate change be changing the terroir expressed by each grape-growing location? That is, the unique terroir being expressed by any given wine must now be quite different to what was happening (say) 30 years ago.

For example, it has always seemed to me that the main difference between the Cabernet-based wines of Bordeaux, and those elsewhere in the world, has been that most wine-makers try to get their grapes fully ripe each year, while in Bordeaux they got them as ripe as the weather would allow in that year. That is, Bordeaux has traditionally been a marginal climate for Cabernet grapes. As Anne Krebiehl put it (The differences between high- and low-elevation wine):

Médoc, also known as the Left Bank of Bordeaux, is one of the lowest-lying wine regions in the world. This enabled grapes like Cabernet Sauvignon and Merlot to ripen in a marginal climate for these varieties before climate change.

Those last three words are the key to this blog post. If climate change has resulted in warmer temperatures, as we are continually being told (and as seems very obvious, anyway), then Bordeaux should no longer be a marginal Cabernet-ripening  region. It might now be warm enough to be a very consistent growing region; and I thought that we might be able to investigate this idea with some data.

Temperature

We should start by looking at the data on global warming. One good source of data is the National Aeronautics and Space Administration, who have a web page on Global Climate Change. NASA uses their satellites to collect all sorts of data about our planet; and the data of interest here refer to what they call their Global Land-Ocean Temperature Index.

I have produced a graph of their published data below (sourced via Statista). The data illustrate the global average land and ocean surface temperature in °C for the years 1880 to 2020. The numbers are presented relative to a baseline temperature, for the years 1951-1980 — that is, they show how much warmer or colder the world is than it was between 1950 and 1980.

The black line represents the temperature, while the pink line is a 15-year running average (ie. the average of the 15 years centered on that point). The dashed line is simply the 0°C (1951-1980) baseline.

The obvious thing to note is that it was colder before 1940 and warmer after 1970. However, we can go further than this. For example, there has been a steady increase in temperature since 1910, with relative stability for the 30 years before that.** Second, there was a big increase between 1939 and 1945 — this shows you what detonating a lot of bombs will do to you even if you are not at the site of the explosion.

However, for our purposes here, the most important point is that there has been a rapid and continual rise in temperature since c. 1977. I was studying environmental science at university at that time, and no-one mentioned global warming. You can see why; and also why it has become a big issue since then.

Vintage scores

Now we can look at some vintage data for the Bordeaux wine region, covering roughly the same time period. I have already presented these vintage-quality data, in a different context, in a previous post: A century of French wine vintages.

The data used here cover the years 1900 to 2019, for the red, white and dessert wines of Bordeaux. The data come from vintage charts produced by the Cavus Vinifera website (Les millésimes en France de 1899 a nos jours), with a quality score out of 20 for each wine type. I have simply averaged the scores across the three charts, for each year.

The next graph shows the vintage scores (vertically) for each year (horizontally). The black points represent the annual data, while the pink line is the 15-year running average (as in the previous graph). The dashed line simply represents the average score across the whole period.

Clearly, as is true for the temperature, the vintages were below average until 1940, and then above average after 1975. There have been no bad vintages since 1993, so that vintage quality is now consistent from year to year (as predicted). However, unlike the temperature, the rapid increase after 1970 lasted only until the mid-1980s, and the scores have remained roughly steady since then (rather than continuing to increase). So, the continued increase in temperature has not helped the Bordeaux vintages during the past 30 years. Perhaps Bordeaux has now already reached its maximum maturation potential?

Looking briefly at the other French wine regions for which there are similar data (Burgundy, Rhone, Alsace, Loire, Champagne, Beaujolais), there has not been a bad vintage since the end of the 1960s, or even a mediocre vintage since the early 1990s, across all of the wine regions. So, our Bordeaux pattern seems quite general — vintage quality in France is far more consistent now than it was before the temperature increase late last century.

Afterword

It would, of course, be very naive to assume that all there is to global climate change is increased temperature. Indeed, our weather systems have become more erratic ("volatile" is the official term), with increased variation particularly in various forms of precipitation — sometimes the rainfall is too much and sometimes too little in Australia and the USA, for example, and hail has become a problem in parts of Europe.

Indeed, Bordeaux is one of the areas affected by increased hail damage, destroying up to 50% of the crop in the past couple of years. The vignerons are fighting back, as best they can (On a balloon and a prayer: Bordeaux grapples with climate change); but it would be a better idea to actually stop the climate change, if we can.

---

* Compare: Terroir and other myths of winegrowing, with Irrefutable proof through detailed chemical analysis that terroir exists.

** Current estimates suggest that this long-term temperature stability goes all the way back to the mid 1400s — i.e. 400 years (see: Proxy-based reconstructions of hemispheric and global surface temperature variations over the past two millennia).

Australian bulk wine exports are economically inefficient

As many of you will know, the Australian wine industry is in big financial trouble at the moment, because the Australian federal government has decided to antagonize the national government of one of its biggest trade partners, China. The source of the underlying dispute is somewhat beside the point, as it has nothing to do with the wine industry, although that industry is being targeted in retaliation.* In a similar manner, the US government is currently targeting parts of the European wine industry, with penalties for things that have nothing whatever to do with the EU wine industry.

In Australia's case, the export of wine is now being seriously compromised (Australian wine exports to China fall by 98 per cent). As a result, wine producers are being encouraged to return to traditional markets including the United Kingdom, the USA, Canada, and Germany. There is also likely to be a drop in grape and wine prices (Red wine prices tipped to plummet as exports to China trickle to a halt). It is therefore instructive to look at the sort of price that the Australians currently get for their exported wines. In this post, I will look at bulk wine exports.

One obvious place to look is what was traditionally Australia's biggest wine export market: the United Kingdom. The British have imported bulk wine from lots of places, because they did not have much of a wine-producing industry of their own, until global warming started to have a detectable effect.

The following graph illustrates the top six importers in 2020 (from Top bulk wine suppliers to the UK, 2019 v 2020). It shows the total amount of bulk wine (horizontally) and the price paid for that wine (vertically), with each point representing a named import country. The pink point represents the total for the remaining countries.

Note that Australia is by far the biggest importer by volume, but the price received is very poor. Indeed, the New Zealand wine garners 2.6 times as much money per liter; and the USA is actually the biggest importer by total value (£123.9 million, versus £122.5 million for Australia).

The Australians will need to do better than this from their remaining trading partners, if they are thinking of continuing to rile some of them. A summary of exports during 2020 is included in: Australian wine exports slow due to China tariffs.

For comparison, we could look at bulk exports from Italy. The next graph illustrates the top 20 importers of Italian bulk wine in 2020 (from Italian bulk wine exports, 2019 vs 2020). It is arranged the same as the first graph, except that only seven of the countries are labeled, and volume uses a logarithmic scale.

Here, Germany imports an order of magnitude more Italian bulk wine than does anyone else, and pays an average that is less than most of the other countries. So, the Italians are not doing so well here, either. Indeed, only three countries pay well above the odds for their bulk Italian wine, including the USA and China. Note that Norway pays more than do the other Scandinavian countries, which pay about average (Sweden is labeled, and Denmark is the point just below the pink dot).

Mind you, it is not at all clear about the fate of the German imports. Back in 2017, this report appeared from Angelo Cotrone (Bulk wine comes into its own):

More than 40% of all wine produced in the world is exported, of which 40% is shipped in bulk, a tendency that’s rising. In some countries, more than 60% to 70% is shipped in bulk. Much of this wine is sent first to Germany for bottling, before being re-exported to its destination market. Germany is a global hub. Over 3 million hL are exported from Germany, but only a third are German wines. 

Germany’s automated bottling lines are so efficient that it costs less for Chile to bottle in Germany and then send the wine back to South America, than for Chile to bottle locally. US wines are bottled in Germany and re-exported to the US. We can bottle wines in Germany for about €0.30 per bottle, and the costs go down with volume. In the US, bottling costs around $1.00 per bottle, with Australia somewhere in the mid-range. Transport is about €0.10 per Litre.

The effect of this eccentric behavior on the global carbon footprint is another thing altogether, of course. You can check out the total wine exports from Germany here: Major export markets for wine from Germany in 2019).

Anyway, a direct comparison with Italy suggests that the Australian bulk wine exports into the UK are actually not too bad, as they beat the price of the bottom nine export countries from Italy; and their UK price considerably beats the Italian export price to Germany, even though the volume involved is roughly the same. The issue, then, is that the Italians are not trying to antagonize any of their wine recipients, and thus disrupting their market.

---

* The ultimate problem was deteriorating trade relations (What does China really want from anti-dumping probe into Australian wine?). This was exacerbated when a politician decided to shoot his country in the head (rather than the more traditional foot, usually favored by politicians) by demanding that China be investigated over the origin of the SARS-CoV-2 virus (see this report from way back in April: Chinese ambassador threatens boycott of Australian wine, and this one from May: China considers targeting Australian wine). No-one demanded this for the H1N1 influenza epidemic (2009), which came out of Kansas, nor the Spanish Flu (1918), which also came out of Kansas. Apparently, some trading partners shall be investigated but not others. Interestingly, much of the Australian wine media seem to be blaming the Chinese for the current trade dispute. Perhaps the most same commentary has come from Jeremy Oliver: Do we want to save the China wine market?

Does bottle price have anything to do with cellaring desirability?

I recently asked the question: How soon is wine consumed after purchase? This inevitably involved the topic of cellaring wines, since most wine production seems to be intended for consumption within 1—3 years of bottling. Indeed, only c. 10% of the people surveyed said that they preferred to cellar their wines.

Having a wine collection seems to be associated with a certain amount of wine snobbery, although we might prefer to see this as "wine interest", instead. Another aspect of snobbery is, of course, cost. Having expensive bottles in the cellar is much "better" than having cheap ones, as explained in Leonard S. Bernstein's 1982 classic The Official Guide to Wine Snobbery.

The obvious question, then, is: Does the wine price have anything to do with cellaring desirability?

One possible source of data to answer this question comes from Wine Ark, one of Australia’s leading wine storage companies. You can read a bit about the company in: A conversation with Wine Ark.

Wine Ark periodically releases a list of Australia's Top 50 Most Collected Wines, based on how many customer bottles they have in their storage. So, I have had a look at Australia’s Most Collected Wines 2019. These are graphed below (in order from the top), along with the Wine-Searcher "Avg. USD Price (ex-tax)" for the most recent vintage release. Note that the price uses a logarithm scale in the graph.

Well, it seems to me that there is not a very strong relationship between cellar popularity and price. For example, the three most expensive wines are ranked 1st, 15th and 21st, while the three cheapest are 8th, 37th and 40th.

However, the top 25 wines are, on average, 50% more expensive than are the bottom 25, at US$121 versus US$88. Furthermore, the rank-order correlation between cellaring and price is 0.274 (p=0.056, for those of you who want to know), indicating a general decrease in price with fewer stored bottles.

So, the answer to the question posed in the title is: Yes, more-popular cellar wines do tend to cost more than less-cellared ones. However, even within a single company wine price does not always correlate with cellaring (eg. the Penfolds wines, and the Wynns Coonawarra Estate wines).

Also, there is not much relationship to availability. Some of these wines are produced in quite large commercial quantities, and are available world-wide (eg. the Wynns Coonawarra Estate wines), while others are much more specialist (eg. the Yarra Yering wines, or the Mount Mary wines).

This leads me to wonder whether it is only Australians who behave like this, or whether this is a much more general cellaring pattern. After all, many people think that an Australian wine cellar must look something like this: