AI better than humans at predicting value of wine, new study finds
Artificial intelligence can be successfully used to predict fluctuations in the price of fine wines, according to a recent study from researchers at University College, London.
In tests, the software proved up to 98% more accurate than its traditional human rivals.
The process involves machine-learning technologies which enable the computer to identify which items of data are most important when analysing movements in price.
The software was tested using 100 of the most sought-after fine wines from the Liv-ex 100 wine index.
The research was led by UCL MSc graduate Michelle Yeo in collaboration with Invinio, a quantitative wine asset-management consultancy founded by UCL academic and former hedge-fund trader, Dr Tristan Fletcher.
Professor John Shawe-Taylor, co-director of the UCL Centre for Computational Statistics and Machine Learning and head of UCL Computer Science, who co-authored the study, said: “Machine learning involves developing algorithms that automatically learn from new data without human intervention.
“We’ve created intelligent software that searches the data for useful information which is then extracted and used, in this case for predicting the values of wines.
“Since we first started working on machine learning at UCL, our methods have been used in a wide variety of industries, particularly medical and financial, but this is the first time we have entered the world of fine wine.”
Yeo commented: “We’re pleased we were able to develop models applicable to fine wines and we hope our findings give the industry confidence to start adopting machine learning methods as a tool for investment decisions.”
The team hopes its technology could be used to help investors make more informed decisions about their wine portfolios and to encourage non-wine investors to look again at the category.
Invinio plans to continue its collaboration with UCL in order to refine the service it currently offers wine investors through its website.
Fletcher founded Invinio in 2013.
The team is now looking to test its technology on other alternative asset categories, such as classic cars.
Via: Google Alert for ML