Tag Archives: wine recommendations

Artificial intelligence and wine recommendations

cooper's hawk
Drinky is embarrassed that his AI brethren think the WC likes buttery California chardonnays.

Wine marketers are betting millions that algorithms will help us find wine we like

Most computer-generated wine recommendations have traditionally been pretty much worthless. There’s this, which we’ve noted before on the blog. But there’s also this, from wine.com, which arrived last month: The email said I would like a $64 bottle of Veuve Clicquot (I think not), as well as a $20 Kim Crawford sauvignon blanc (I think not, again), as well as a $12 California pinot noir and a $12 sweet red blend (I really, really think not).

That’s because the formulas used to put these recommendations together depend on things that aren’t necessarily related to wine – like income, age, and gender — and use past purchase information probably more than they should. Just because I bought wine A doesn’t mean I’m going to like it enough to buy wine B. And AI-generated recommendations have been notoriously lousy at using price to determine what we’ll like.

In addition, most algorithms have not been able to effectively process the wine-related criteria that do matter, like style, alcohol levels, and so forth. And I’m not sure that marketers understand the challenge. One highly-touted AI effort in 2021 said the the goal was “to personalize wine recommendations based on individual preferences, for example: Is the subscriber a red wine or do they prefer white (or maybe a little of both)?” Which seems more of a 1990s approach than something in 2021.

Another, the BottleBird app, asks a series of questions to find out what we like, including “How do you feel about the smell of flowers?” How we answer, says its publicity, will make sure we “never buy a bad bottle of wine again.” So, of course, when I tried the app, I got a 97 percent match with two Fre non-alcoholic reds and two buttery California chardonnays. Hardly the WC’s kind of wines, are they?

The process is so difficult, in fact, that a friend of mine who has written extensively about the subject once told me the only way AI wine recommendations could be successful is if they included information from human tasting panels. Which hardly sounds very AI.

So why have wine marketers spent millions of dollars trying to find a way to teach machines to make wine recommendations? My hunch is that it’s not so much about helping us find wine we like as it is selling us wine. Which, of course, is not necessarily a bad thing – if they work. But when they recommend wines I wouldn’t buy even if they were free, what’s the point?

Winebits 458: Wine recommendations, alcohol levels, natural wine

Wine recommendations

This week’s wine news: Wine recommendations most of us can’t afford, plus the feds help with alcohol levels and the market for natural wine

• Pricey, pricey, pricey: How about a list of fall and winter wine recommendations where all but four of 20 wines cost more than $20? Sadly, that’s what happens when you ask restaurant wine types for wine advice. It’s not that there aren’t some excellent wines in the post from Bloomberg News (the $22 Domain Berson Chablis, for one) and that these people don‘t know their business, but let’s be honest. I didn’t want to spend $145 for my once in a century wine if the Cubs win the World Series; who is going to do it because the weather is cooler? Making matters worse is the headline: “20 wines you need to drink this fall.” No I don’t. The only one who got the pricing right was Ryan Arnold of Lettuce Entertain You, a restaurant company in Chicago started by one of the world’s great restaurateurs, Rich Melman: a $16, a $17, and a $30 wine.

• More accurate: W. Blake Gray reports that a change in the way the federal government approves wine labels will mean more accurate alcohol percentages on the label, and perhaps the end of the ubiquitous 13.5 percent. “In many cases wineries have to submit the label for approval before the final blend of the wine has been decided,” he writes. “They have to guesstimate how much alcohol the actual wine will have. That means label approval has driven many winemaking decisions, which is bad for everybody.” Now, since they won’t have to list the alcohol percentage to get the label approved, they can make the wine and put the correct alcohol level on the label afterwards. That’s not only better for producers, but consumers as well. One reason we see 13.5 percent on so many labels, even if the wine isn’t really 13.5 percent, is that it’s easier to do that for a variety of complicated and legal reasons.

• Not too many people: The Wine Curmudgeon frequently laments the wine fads passed along as fact by the the Winestream Media, and it’s a pleasure to see a serious discussion about whether natural wine is anything more than one of those. “Are sales in this niche finally starting to have a global impact – or is it just a hipster bubble that could burst as fast as a poorly made pet-nat?” asks the Wine Business International trade magazine (full disclosure: I freelance regularly for the magazine). The conclusion: Assuming one can define a natural wine, since there is no accepted standard other than an organic wine isn’t natural enough, “market share in most countries has yet to reach even the first percentage point.” Case closed. Now we can go back to arguing about something important, like the efficacy of scores.

Get out of your wine rut

wine rut
“I’m so tired of merlot, but what else is there to drink?”

The only rule of wine that counts — really, the only rule there should be — is to drink what you want, but to be willing to try different kinds of wine. How else will you find out what you like unless you taste something you’ve never tasted before?

Needless to say, given the foolishness that passes for so much wine advice, that’s easier said than done. Is it any wonder that so many wine drinkers give up, confused by toasty and oaky and cigar box aromas? Or that craft beer, because beer is so much easier to understand, could be bigger than the entire California wine business by the end of next year?

Which was the reason for “Get out of your wine rut!“, which I wrote for the Bottom Line Personal newsletter. Regular visitors here might recognize some of the wines I recommend, but the point of the article is about more than the wines. It’s about trying something different because there are thousands of wonderful cheap wines that you might like, if you’ll only give them the chance. Among the suggestions:

? Chenin blanc instead of chardonnay, if you’re looking for something lighter and more fruity. As noted here many times, dry chenin blanc deserves much more attention than it gets.

? Red Rhone blends instead of merlot. These French blends, like the legendary Little James Basket Press, can have more interesting fruit flavors but still offer the merlot softness that many of us like.

? Albarino, the Spanish white, instead of sauvignon blanc. Albarino should be the next big thing, instead of something as old and tired and as hard to find as gruner veltliner, because it offers quality at very affordable prices and is on more store shelves than you’d think.

Winebits 372: Valentine’s Day wine 2015

Valentine's Day wineA look at Valentine’s Day wine suggestions from around the Internet, because the Wine Curmudgeon doesn’t want to do it himself, given this is The Holiday That Must Not be Named:

? From a supermarket: HEB, the Texas grocery store chain that is one of the largest independents in the country, focuses on sweet and cute, including chocolate-flavored wine. I’m not sure there is anything here I would recommend, but the Wine Curmudgeon is not the target demographic for this post. Also note how the post uses descriptors that focus on sweet, like candied fruit. Anyone who wants to know why sweet red wine has become such a cash cow need only look here.

? From a wine magazine: Decanter, the British equivalent of the Wine Spectator, sticks to sparkling wine, but includes cava and Prosecco, including “10 great value Cavas” and English sparkling wine. The point here is not whether these wines are available in the U.S., but that the editors understand not everyone wants to spend $200 on a bottle of Champagne. Would that wine magazines in this country took the same approach. My favorite pick? The Jansz sparkling from Tasmania, about $20, which I drank on New Year’s as part of my Champagne boycott.

? From a financial news website: The Street runs a lot of wine-related items; why is anyone’s guess. But most of it is solid information, and its choice of 11 Valentine’s Day wines is more of the same. The 11 wines are mostly white, mostly quality (though not always easy to find), and mostly around $40. Having said that, the Marcel LaPierre from Morgon in Beaujolais, about $30, is an impressive recommendation.