What should I wear today? The answer to one of life’s big questions could came from an algorithm created to solve all your fashion problems. Researchers from Spain’s Institute of Robotics and Industrial Informatics, along with colleagues at the University of Toronto, have developed a mathematical model that is able to assess whether a person is fashionably dressed and to give advice on how to make the outfit more trendy.
They created an algorithm built on a detailed analysis of a dataset containing 144,000 user posts from fashion website chictopia.com. To turn the data into a mathematical model for trendiness, the researchers used a deep neural network coupled with a conditional random field, which helps the computer learn how random elements, such as geographic location, background scenery and ethnicity, do or do not predict how fashionable a post is. The learning process considered not only what was visible in the photos but also the number of “likes” received, the tags and any accompanying comments or descriptions.
The algorithm was able to learn how fashion varies by season and city and even age group. Armed with this knowledge, it can now predict whether a given outfit would be deemed stylish and offer suggestions for how to dress more fashionably.
The aim of the work is to build mathematical models capable of understanding what makes a particular clothing item fashionable or unfashionable, and based on that, to make recommendations on how to dress. Fashion critics have questioned the algorithms credibility, arguing that fashion is an art and an expression of personality. Would you hire a machine as your personal stylist and let it tell you what you should and should not wear?