MyDataModels AutoML enables industries of all kind and size to access the power of Small Data forecasting. Explore our use cases and discover how MyDataModels solutions can solve your business issues.
Be part of the AI/Machine Learning revolution
Can wine quality be ‘predicted’ through the use of machine learning?
Only a small percentage of the wines produced around the world increase in value. And to be sold successfully, the wines must be impeccably stored, have traceable provenance and generally be offered in their original wooden cases. To reach such a high quality, hence price level, the initial quality of the wine and its potential to age beautifully has to be evaluated when young. Although specialised wine tasters have the skills to identify these high potential wines, most vintners, wine production managers, wine makers, wine resellers, cellarmen, wine traders, wine stewards can use some support in assessing the potential of a young wine. The choice of a ‘future’ high quality wine is very complex.
While wine production managers and wine quality control engineers can get actionable predictive guidance to help them control the quality of their wine all along the wine production process through the use of machine learning, wine tasters, vintners, wine makers, wine resellers, cellarmen, wine traders, wine stewards can also use predictive models to get quality insights on the young wines. However, they are usually not data scientists and they often do not have the required skills in machine learning or the software coding experience to build predictive models. Most of the time, they have historical data about their own past wine productions and/or other vineyard productions. These data imply such components as the acidity of the young wine, typically the titratable acidity naturally present in the grapes or created through the fermentation process. But also volatile acidity caused by bacteria, and citric acid generally present in very small quantities in wine grapes. Residual Sugar is also a major component, it refers to natural grape sugars contained in the juice of wine grapes and used up by fermentation as the yeasts to feast upon. Another component is chlorides which is usually an indicator of the wine’s “saltiness”. Sulfur dioxide is the most common preservative used. Other wine components measured all along the production process include pH and alcohol.
The data trawled by these wine professionals are Small Data, meaning they often contain historical data about a few dozens or hundreds of different wines but rarely thousands or more like in Big Data. Traditional machine learning tools work well with Big Data but do not perform as well with Small Data.
MyDataModels allows wine professionals such as wine production managers, wine quality control engineers, wine tasters, vintners, wine makers, wine resellers, cellarmen, wine traders, wine stewards to build predictive models from Small Data in a nimble way. The wine professionals do not need to undergo any kind of training. They can use their collected data directly, without normalization, outlier’s management or feature engineering. Thanks to this limited data preparation, the results from this specific dataset were obtained with a few clicks in 3 minutes on a regular laptop.
MyDataModels brings a self-service solution for those who have Small Data and no data scientists.
When it comes to winemaking and wine choosing, know how is everything. No machine can ever replace a vintner’s well trained palate, nor the knowledge which has been passed from generation to generation within a family of wine savvy gourmet producers. Not everybody in the wine industry has the same amount of knowledge. Nor can every vineyard afford the same level of wine connoisseur’s as wine managers that the Château Mouton-Rothschild vineyard can afford.
Yet it is possible, accessible and efficient for the wine professionals to use machine learning in order to anticipate the wine quality. For instance, in this red wine quality prediction use case, the results obtained from MyDataModels’ predictive models are very good with a 0.63 Root Mean Square Error. It means that in the estimation of the wine quality grade ranging between 0 and 10, the average error made is of 0.63 point out of 10, or in other words 6.3%. To rephrase this, it is an excellent result.
“Predictive model reached excellent result on wine quality predition”
In May 2016, Sotheby’s New York auctioned 20,000 bottles of fine and rare wine. The seller was billionaire collector William Koch. The cellar went for a total of $21.9 million, surpassing the presale high estimate by 46 percent. And among the star wines sold were 10 bottles of Château Mouton-Rothschild 1945. They went for $343,000, therefore doubling the presale estimate of $120,000.
Using MyDataModels application empowers most vine professionals to produce or identify the next Château Mouton-Rothschild 1945.
Make your business go further.
You don’t have data here and now?
No problem, data are available to make your test as relevant as possible!
© MyDataModels – All rights reserved | Credits | Terms of use | Privacy and cookies policy
