Sign In

Communications of the ACM

ACM TechNews

Researchers Taught an Algorithm to 'Taste'

View as: Print Mobile App Share:
A woman tries to choose a wine to purchase.

Scientists have demonstrated that adding a new parameter to the algorithms that run many wine apps use can make it easier to find a precise match for your own taste buds.

Credit: Kvinde/Getty Images

Scientists from the Technical University of Denmark, the University of Copenhagen (UCPH) in Denmark, and the California Institute of Technology taught an algorithm to better predict an individual's wine tastes.

The researchers held wine tastings for 256 participants, who were asked to arrange shot-sized cups of different wines on sheets of paper based upon which wines they thought tasted most similar.

The researchers then digitized the points on the sheets of paper and incorporated the data with hundreds of thousands of wine labels and user reviews provided by Vivino, a global wine app and marketplace.

Said UCPH's Serge Belongie, "We can see that when the algorithm combines the data from wine labels and reviews with the data from the wine tastings, it makes more accurate predictions of people's wine preferences than when it only uses the traditional types of data in the form of images and text."

From University of Copenhagen (Denmark)
View Full Article


Abstracts Copyright © 2023 SmithBucklin, Washington, D.C., USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account