Communications of the ACM
Big Data May Be Fashion Industry's Next Must-Have Accessory
The Force Atlas algorithm visualizes the layout of a network.
Credit: Gephi Consortium
Pennsylvania State University researchers have used data analytics to identify a network of influence among major fashion designers and track how style trends move through the industry. Led by Penn State professor Heng Xu, the team analyzed 6,629 runway reviews of 816 designers from Style.com, covering 30 fashion seasons from 2000 to 2014. The team extracted key words and phrases, added them to a dataset, and then created an approach to rank the designers and map influences within the group.
To assess the accuracy of the model, the team compared the network against three industry-recognized lists of influential designers; they determined the network closely matched these lists. "There is no one gold standard for the most influential designers, but we believe these are a good place to start a comparison," Xu says. She believes industry professionals could use the technology to predict fashion trends and identify up-and-coming designers.
Xu sees the fashion industry one day analyzing real-time data from Twitter, Pinterest, and Instagram to predict fashion styles. In addition, she says the technology may assist consumers by helping them create wardrobes that are both in their budget and in style.
From Pennsylvania State University
View Full Article
Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA
No entries found