Wine Competitions, Austria, Sauvignon Blanc, Südsteiermark, Wine, Wine Reviews, Wine Tasting
Comment 1

Wine Competitions Adopt AI Metrics for Transparent Results

In 2021, the prestigious Concours Mondial de Bruxelles (CMB) wine competition began using artificial intelligence (AI) developed by Winespace, a Bordeaux-based firm founded by Sylvain Thibaud and Julian Laithier in 2015. This AI was integrated into the judging protocol as a value-added feedback mechanism for producers, allowing for a more comprehensive understanding of wine assessments. CMB also collaborates with UC Louvain in Louvain-la-Neuve, Belgium, on further analysis, which evaluates the performance of its juries and judges, enhancing the reliability of the results.

I first experienced Winespace’s rubric for sensory analysis when judging the México Selection by CMB, held in Guanajuato, Mexico, in 2021. At the time, its technology was a promising prototype, and the collaboration with CMB helped Thibaud and Laithier to commercialize what is now a robust platform called Tastee AI that has since been adopted by CMB and others.

Thibaud and Laithier developed Tastee AI for use in generating metrics and performance metrics for wine competitions.
Winespace’ Sylvain Thibaud (left) and Julian Laithier.

In April 2024, I used the tasting grid again during the Sauvignon Selection by CMB, one of CMB’s five annual wine competitions, held in Leibnitz in the Austrian state of Styria. This time, a panel of judges recorded tasting notes in as many as eight different languages, showcasing the international nature of the competition. The technology seamlessly translated and analyzed those notes, compiling an at-a-glance sensory analysis for each wine.

Wine competitions generate analysis for producers

According to Thibaud, the resulting reports, which have been shared with producers for the past two years, offer a collective picture of the wine’s quality and style. This is presented in the form of summarized tasting notes, an aroma wheel that visually represents the wine’s aromatic profile, a list of specific strengths and weaknesses, and constructive comments for improvement.

Aroma wheels generated by Winesense for the CMB wine competition.
Winespace’s aroma wheels for two entries in the Concours Mondial des Bruxelles competition—one white wine (left) and one red, illustrating the complexity and diversity of the wines evaluated.

“From the CMB’s point of view, this approach also reflects a desire for transparency in the wine assessment process,” Thibaud observes. This transparency not only reinforces the industry’s confidence in the seriousness and value of the medals awarded but also educates consumers about the evaluation process, making the results more meaningful and trustworthy.

In the future, Winespace plans to provide feedback to each judge on their taste preferences, scoring style, and other criteria. “One of the aims of analyzing comments is to identify the preferences and writing habits of each taster,” explains Thibaud. “This insight will help professionals who judge wine competitions refine their evaluation skills and become more consistent in their assessments. We can also identify the criteria they seem less sensitive to and areas where they are less expressive,” allowing for targeted training and improvement.

This type of rigorous analysis soundly debunks the commonly held belief that wine sensory evaluation is purely subjective. For example, analysis of my five-person jury for the 2024 Sauvignon Selection competition revealed a highly correlated panel working with astounding consistency. The data showed that even with differing personal preferences, judges could arrive at similar conclusions about wine quality, demonstrating a shared understanding of the evaluation criteria.

Eggshell plot depicting the performance of a five-person panel when judging a wine competition.

The eggshell plot depicted to the right illustrates the performance of a coherent jury, one that arrived at a consensus in their scoring when evaluating wines of the same or similar quality (namely Sauvignon Blancs from world-class regions). The panelists’ close alignment is represented by the cluster of jagged curves just above the smooth curve, which is the control metric for a theoretical jury with identical scores. This data provides critical insights for improving future competitions and refining the judging process.

Metrics of this caliber could help the industry address valid concerns about inconsistency in scoring caused by the different models and scoring systems used by commercial wine competitions. By implementing a standardized approach, competitions can enhance their credibility and provide more reliable results, ultimately benefiting producers and consumers alike.

The integration of advanced analytical models and AI technologies in wine competitions marks a significant shift towards transparency, consistency, and education in the wine industry. As these methods continue to evolve, both producers and consumers stand to benefit from a more nuanced understanding of wine quality and preferences, ultimately leading to an enriched wine culture.

Moreover, the role of education cannot be underestimated in this process. Educating judges and producers alike about the importance of consistent, objective scoring will help maintain high standards across competitions. Workshops, seminars, and training sessions can foster a culture of excellence and ensure that all parties involved are equipped with the necessary skills and knowledge.

Additionally, as wine competitions evolve, the integration of technology will likely lead to a more sophisticated understanding of consumer preferences. By analyzing trends in tasting notes and scores over time, competitions can help producers align their offerings with market demands and changing tastes. This proactive approach will not only elevate the quality of wines but also enhance the overall consumer experience.