Called Invinio, it uses a system of “machine learning”, which is based on algorithms that automatically learn from new data without needing any human intervention. The intelligent software can draw conclusions from this data and use it to predict values with unprecedented accuracy.
During a trial of the system, the results of which are published in the Journal of Wine Economics, the machine routinely outperformed traditional prediction techniques not involving AI. On average, there was a 15 per cent improvement in predictive accuracy.
“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,” said co-author John Shawne-Taylor
For those who have an interest in investing in booze, it's great news. For the merchant who earns a living by providing investment advice, it can only mean one thing – machines could soon steal their jobs.
And why stop there? There's every chance that, one day soon, the same value monitoring and prediction technique could be used on other investable items such as classic cars.
Michelle Yeo, one of the lead researchers, said:
Other areas of finance already use automated processes for identifying meaningful trends but these haven't been tested on the fine wine market until now.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.