Monday, April 25, 2022

Wine recommenders are no longer people

Back when I was young, getting a recommendation for a good wine involved walking into a shop full of bottles, and being pounced upon by an eager young man, who tried to help. If you were in a restaurant, instead, then a man in a suit suggested the sort of wine you could never afford. Alternatively, you asked a knowledgeable friend; or you went to an actual winery, to see if they have something you like.

These days, you use an app or a web page. Social interactions have moved in this direction during my lifetime — no longer do we look people in the eye, but we stare at an electronic screen, instead. How does anyone get married, under these circumstances?

Well, there seems to be several quite different ways wine recommendations can be achieved via computing, and I will look briefly at them here. They are not all equally successful (or even easily understood).

First, however, we need to consider what we are using the recommendation for. Am I just looking for a wine to add to my collection, to drink at some future (appropriate) time? If so, then a suggestion from a (suitable) wine commentator is probably what I need. Am I looking for a wine to drink with dinner tonight? In that case it is quite different, because I (presumably) would like to end up with a specific wine, that either goes with the food or impresses the pants off my host. It seems to me that we lump these two extremes together, along with everything in between; and this confuses the issue.

Moreover, there are several possible criteria for choosing a wine. We could, for example,  focus on quality, or we could focus on suitability for the occasion, or we could focus simply on whether we actually like it. These criteria do not necessarily need to coincide in terms of choice, under any given circumstances, although it seems desirable that they should do so as often as possible.

The matter of pairing wine with food seems to be a particular bug-bear. At one extreme, it is perfectly simple. For example, if I am going to eat a light white fish in butter sauce, then a hearty red wine would mean that I can’t taste the fish at all. On the other hand, my wife and I have a Sicilian recipe, originally for swordfish but we use it for tuna — it has a lot of strong ingredients, like tomatoes and capers and celery, and I would never be able to taste a light white wine against it. Pairing does not have to be more complicated than this.

On the other hand, sometimes getting the tastes to pair nicely is more tricky. We also have a duck recipe, with which it is suggested that we pair a Pinot Noir. I could not find one in the house, the first time we tried it, so I chose something else. It was a nice wine; but alternating a sip of this wine with a mouthful of duck did not enhance either product. Next time, I made sure I had a Pinot Noir — and it was perfect.

Given the above considerations, there are basically only four types of information that can be used to recommend a wine:
  • Quality — scores or descriptions
  • Detailed oenological characteristics
  • Similarity to your known wine preferences
  • Similarity to other people’s preferences

All four of these fail, in one way or another. That does not surprise you, because otherwise we would already have a universal wine recommender by now. So, let’s look at them, one by one.

Quality, variously defined, has traditionally been at the heart of wine recommendations, since time immemorial. It is at the basis of all definitions of fine-wine regions, it is the basis of all wine scoring systems, and it usually is the basis of most wine writing. In the past, Baby Boomers preferred scores (It isn’t polite to point), but these days Millennials apparently prefer words (The importance of online reviews). For a range of suitable recommendation sites, consult: The top wine apps to help pick your bottles. Even putting aside the idea that most wines are never reviewed, and that many reviews might be fakes, the basic issue is still that wine commentators all have different opinions, many of which reek of unadulterated snobbery. As a result, the wine industry has a pretty atrocious reputation — trying to reach “normal people” seems to be an uphill battle (How did Australian beer slobs become wine drinkers?).

So, wine recommendations based on quality miss the basic point — most people care more about value for money than about quality per se. There are definitely web sites based on this idea of value, and they have been successful. However, they all cover geographically and temporally restricted locations. For example, I choose newly available wines based on value for money suggestions from local writers here in Sweden — if two of the three agree, then I am likely to try a bottle. This only works here, and it only works for the few weeks that the wines are available. This is not a general recommendation scheme.

The second recommendation approach is to break the thing being recommended down into each of its minute components, and then try to match those components to the recommendation required. For example, The Music Genome Project claims to be the most comprehensive analysis of music ever undertaken, treating it like a study of the genes in your own body. Your genes, inherited from your parents, act together to create yourself; and we therefore are very interested in studying them, to see how they work. The idea is to do the same thing for music, based on all of its acoustic elements; and the same can also be done for wine (eg. Tastry AI).

The basic problem here is that neither music nor wine exist for us outside of our own minds. That is, our ears detect the sound waves of music, but they then convert them into electrical signals, which they transmit to the brain. Thus, it is our brain that interprets the electrical signals, and calls some of them music and some of them cacophony. The same applies to taste. Atomizing music or wine into the basic components that exist before we hear or taste them deals only with the first part of the experience (Why wine is tasted with your brain, not your palate). The role of perception in food and wine evaluation cannot be over-estimated.

The third approach to recommendation is simply to get you to decide what you like (or want) and then find other products that seem to be similar (eg. My WineGenius). That is, you rate your experiences in some way (words or numbers), and this is used to provide you with new suggestions (these days, based on the computer techniques of artificial intelligence and machine learning). This approach suffers from the same problem as above, that our perceptions occur in our minds; and there are lots of extraneous things that can affect what our minds perceive. Different circumstances lead to different perceptions, so that time, place and prior information all play a role in what we think we like, on any given occasion (eg. The taste of wine can be influenced by music; How Brahms might make your wine taste better). What we liked last time is not necessarily the same as next time.

The fourth approach is somewhat similar to the third one, but instead is based on matching you to other people. That is, you all rate your experiences (using words or numbers), and these ratings are then used to match you to other similar people (once again, via artificial intelligence and machine learning). The recommendations then come from things that those other people rated highly but which you have not yet rated.  Perhaps the most (in)famous example of this is movie recommendations from Netflix, but Amazon recommendations work the same way. So, naturally, this approach can be applied to wine (The path to Netflix-quality wine recommendations leads through the doors of perception).

This is sort of how marriages work (as mentioned above). You find someone whom you like, and then see how many things you have in common. The more you find, the better the relationship seems to work, long term. Now, obviously, this analogy breaks down pretty quickly, because married people have to change, in order to adapt to each other’s differences; and the more you adapt, the longer things seems to last. This does not apply to drinking wine, of course, since the wine completely fails to adapt to us. Nevertheless, people are prepared to have a go at this approach, for wine (eg. Clans: The intersection of AI/machine learning with behavioral science).

There are lots of different wine recommendation systems out there; and I have mentioned only a few specific ones here. The problem with all summaries of specific recommender systems is that they have a particular agenda — to sell you their particular recommender (and not any of the others). As such, they are very vague, being based on hyperbole rather than information.

So, should we remain optimistic about the idea of a general wine-recommendation system? Well, I still maintain that if we are likely to get one, then we would already have it by now. Sommeliers have been around for a very long time, and they may slowly be getting replaced by computerized systems. However, that does not make the recommendations any better (or worse). As for myself, I still prefer interacting with people rather than computers.


  1. One of the most overlooked books on developing one's wine tasting skills was researched and written by Andrew Sharp, titled "Winetaster's Secrets."

    Robert Parker's book review:

    "An extremely well written book with the most informative and perceptive chapters on wine tasting I have read. This is the finest book for both beginners and serious wine collectors about the actual tasting process -- lively, definitive and candid."

    You can find it published in hardcover and softcover on Amazon, Biblio and eBay.

  2. Adding to the bibliography . . .

    "The Taste Of Wine Isn't All In Your Head, But Your Brain Sure Helps" | NPR News (April 3, 2017)


    "Wine Tasting Engages Your Brain More Than Any Other Behavior, Says Neuroscientist" | Food & Wine (November 26, 2018)


    "Neuroenology: how the brain creates the taste of wine" | Flavour (March 2, 2015)


    You can read Gordon M. Shepherd's book titled "Neuroenology: How the Brain Creates the Taste of Wine"


    You might consider reading his earlier book titled "Neurogastronomy: How the Brain Creates Flavor and Why It Matters"


    ‘Neurogastronomy: how the brain creates flavor and why it matters’ | Flavour (Nov 1, 2012)


  3. Thanks for this extremely thorough and thought-filled analysis. Let me see if I can describe how useful guidance might be accomplished.

    I recommend we begin by distinguishing intrinsic style from situational awareness. Though I share your disdain for many of its practitioners, I find myself defending the notion of the 100-point system for established regional styles, most of which reside in Europe, though there are American examples such as Amador Zinfandel, the Amarone of America (with laudable exceptions such as Scott Harvey's Eurocentric style).
    Even an intermediate wine geek will know hundreds of appellation styles from Chianti to Barolo and Mosel to Meursault. You and I can talk about the fruity purity of Vouvray vs the complex structure and sur lie character of Savennières, just up the river and both Chenin Blancs. We can also contrast the utter masculine raciness of Chinon with the soft, warm comeliness of St. Emilion, (the Cab Franc composition being beside the point.)

    These can be rated based on their trueness to type. Ch. Latour is a lousy Beaujolais. Europe has completed an establishment of styles only just begun in the New World, but we are closing in on it, and in the meantime, we can use the established styles to create a flavor space similar to what Pandora is doing. If the consumer defines a "station" called "Fred's crisp whites," anchored on Mosel and Albariño, the AI can suggest wines that are proximate in the flavor space such as Iowa La Crescent and Texas Picpoul Blanc that the consumer may never have heard of.

    When you speak of the influence of the environment of consumption, you are introducing the need for a different skill which applies to all art. It doesn't belong in your argument. The consumer needs to "feng shui" the environment in which the wine is consumed. Check out for free Spotify playlists Dwight Furrow and I have provided as a beginning.

    1. Thanks for your thoughtful comments. I agree with much of what you say.

      However, you focus on differences among wine styles, and how consumers might distinguish them and evaluate them. Successful recommendation, on the other hand, needs to focus on whether the consumer “likes” the wines, and would want to be recommended any of them. What seems to be a problem, then, is that people are not consistent about their likes, and their likes do not necessarily match those of other people.

      Thus, perception of wine is not only about wine differences but also about wine preferences. That is, people are not really interested in wine styles, but only whether they like any given wine (no matter what its style).

      Being recommended a wine they don’t like is then a failure of the recommendation system, whether it comes from a person or not. Wine seems to be one of the hardest to achieve success.

    2. Hm. I don't think the problem you alude to is particular to wine. The unpredictable finickiness of preference extends to all things aesthetic. Sometimes we can trace the cause. I have a negative reaction to lavendar because my grandmother was a lousy babysitter when I was four years old and used to lock me in a closet when she went shopping, so I would sit there for an hour smelling her sachet and staring at an exposed bulb. I relive that experience every time I smell an Anderson Valley Pinot Noir.
      Most people are crazy about vanilla and cherry unless they were administered flavored medicines when sick as a child.
      Sometimes its consumption environment is simply bad for the wine. My research with music shows that a cognitive dissonance that appears nearly universal can be induced by a musical mismatch. Take a look at how astringent a Cabernet Sauvignon becomes when tasted with a polka!
      Now, it's possible that you enjoy astringency, in which case all bets are off.
      It's clear to me that this area of personal preference is something independent of stylistic trueness. The latter can be well addressed as I've described. So can the former, but only with the participation of a consumer trained to tweak the experience, for example with music.
      This is what I meant by intentional "feng shui," and it applies to all things - an art in itself that is studied and mastered in Asia. It can be a lot of fun to horse around with. An essential starting element is to know what style of wine we are dealing with.
      There is another element at play having to do with acquired tastes. In the mid '70s, I got a handle on most of the popular varieties, but I couldn't grok Sauvignon Blanc. I asked six merchants to recommend to me their 4 favorite SBs. I drank nothing but SB for a month, and I still didn't get it. Then I went by Darryl Corti's shop in Sacramento and asked him the same question. He replied that I only needed to try this one wine, a 1973 Montevina SB by Cary Gott. He had bought the entire vintage. So I took a bottle home and by chance, happened to buy some BBQ'd pork buns in Oakland Chinatown. I can still taste that delicious combination. Moreover, I have loved every SB I've had since.
      I'm pointing at the importance of having a peak experience that gets you into the aesthetic room where you can create a rich body of distinctions that allow you to tell good from bad. Half-shell oysters are another example. I'm still working on a hiphop tune that takes me there.
      I'm taking the trouble to engage with you because of your love for numbers. I think the use of multivariate statistics can be used to create a "Personnal Sommelier" flavorspace similar to Pandora. Perhaps we can work together on this.

    3. I agree that the issues that I raise here do not apply solely to wine recommendation, although they are clearly very important for it.

      Yes, it would presumably be possible to use multivariate analysis of flavours, to summarize the data. Whether this could be used for recommendations is another matter. The important thing to keep in mind is that it is flavour preferences that are most useful for recommendations (at least according to Netflix).

    4. Dear Unknown at 9:18 PM:

      You write:

      ". . . My research with music shows that a cognitive dissonance that appears nearly universal can be induced by a musical mismatch. Take a look at how astringent a Cabernet Sauvignon becomes when tasted with a polka!"

      There are proponents for playing music for their grape vines:

      "Does playing classical music to vines make for better wine?" | Grape Collective (Feb 13, 2014)


      More power to them if -- somehow -- it produces more aromatic or flavorful grapes.

      (Care to share more info on your wine and polka music "field research" . . . and self-disclose your identity?)

      ~~ Bob

    5. This is a seperate realm about which I have no opinion. It's addressed in The Secret Life of Water by Masaro Emoto, reports of the effects of playing music to vines and other plants, and many other studies regarding the physical interactions that may occur due to resonances. These may have something to them or they mightg be all hogwash. I take no position.

      This realm has nothing whatever to do with the cognitive effects I study. I make no claims that the effects I observe are anything but neurological.