Fashion designers and fashion houses usually start conceptualising and designing products for the new season six months to one year prior to the actual selling season–though in recent times this has been drastically reduced with the emergence of fast-fashion retailers. That’s why for most apparel retailers, and the fashion industry in general, knowing the trends customers would like to wear next season is extremely important. In this talk I will describe how modern AI based tools which can understand fashion images and articles can be used to provide a more a more data-driven approach for trend analysis and forecasting. I will describe some of our recent collaborations with various fashion designers.Traditionally a lot of fashion houses send fashion experts to the big four major runway shows who actually observe what is being shown and form very subjective opinion of what are the mega trends that are emerging. While there is great value in expert fashion observers they will invariably limited by how many shows they can see. It is probably not possible for someone to manually look at 20-50 thousand images coming out from the runway shows. We take a more data driven way where we can crunch all the images and then provide these trend reports to the observers who can now have a more data driven backing to their gut instincts.
For more details see https://cognitivefashion.github.io/
Vikas C. Raykar works as a research scientist at IBM Research, Bangalore, India. An expert in machine learning he is currently focused on building machines that can understand natural language and images in par with humans. He finished his doctoral studies in the computer science department at the University of Maryland, College Park. He is also defining a roadmap for what can be done for the fashion industry, primarily leveraging deep image and text understanding together with other cognitive capabilities.