Eye on AI - May 17, 2019
Welcome to Aigora's "Eye on AI" series, where we round up exciting news at the intersection of consumer science and artificial intelligence!
This week we springboard off last week's focus on augmented reality (AR) to consider virtual reality (VR) and its use in product testing. We begin with an excellent review article by the European Sensory Network on the use of VR for sensory research. At the heart of the article is a comparison of beer evaluation in five conditions ranging from central location testing (CLT) to actual in-bar testing, with various levels of VR bridging the gap in between. According to the article,
"Do the results encourage the use of VR in sensory research? Yes – they demonstrate that immersive contexts can easily be used in sensory testing, that they mimic real-world testing at a lower cost and with better standardization. Also, the new methods make us aware of the danger of translating a finding from the laboratory to real life."
Pivoting off of VR and back to artificial intelligence proper, this week brought a potentially significant advance in the area of quality testing, with the South China Morning Post (SCMP) reporting success with an AI-powered taste testing for quality. While the e-nose and e-tongue concepts are not new, they have only found use in limited applications. This new research promises more extensive use, with the SCMP reporting:
"More than 10 traditional Chinese food manufacturers that have taken part in a government-funded AI-tasting programme for more than three years are reporting significantly better profits, paving the way for mass application of the technology, the China National Light Industry Council said in the report."
In much the same vein, Microsoft announced this week that they are partnering with Mackmyra Whisky and Finnish tech company Fourkind to develop whiskey recipes using machine learning. According to Microsoft:
"Currently, the distillery's machine learning models, powered by Microsoft's Azure cloud platform and Azure cognitive services, are fed with Mackmyra's existing recipes (including those for award-winning blends), sales data, and customer preferences. With this dataset the AI can generate more than 70 million recipes that it predicts will be popular, and of the highest quality based on what kind of cask types there are in the warehouse. This is not only faster than a person carrying out the process manually, but thanks to the algorithm's ability to sift through and calculate a vast amount of data, new and innovative combinations that would otherwise never have been considered, can be found."
On a related, but smaller-scale note, the Robb Report reported this week that B Cellars, a Napa winery, turned their business around through the use of large-scale textual analytics.
Finally, it's worth noting the interaction that's happening between the leveraging of influencers for marketing and the AI-based analysis of influencer data. For example, Marketing Week reported that General Mills is investing a full one-third of their digital marketing budget for their organic business in influencer-based marketing. Because the social media data from influencers are so readily available, it's natural to use machine learning strategies to both identify key influencers and to optimize the success of influencer-based marketing strategies. For a starting point on this topic, we recommend this review article by digital marketer Shane Barker.
That's it for now. If you'd like to receive email updates from Aigora, including weekly video recaps of our blog activity, click on the button below to join our email list. Thanks for stopping by!