Designers and fashion houses usually start conceptualizing and designing products for the new season six months to one year prior to the actual selling season. However, the instant gratification of e-commerce and niche direct to consumer brands fueled by social media influencers have made a major impact on how fashion trends are introduced to stylish consumers.
The IDC has found by 2019, about 40 percent of retailers will develop a new kind of customer experience based on an AI platform and hyper-micro personalization can provide a 30 percent conversion increase. To deliver that kind of customized and differentiated experience at scale, designers can use computer vision, natural language understanding, and deep learning to produce and use key insights on trending colours or unique AI generated prints or patterns. This can help expedite the initial design process and better predict demand for hyperlocalized products.
To demonstrate these capabilities, IBM, Tommy Hilfiger and The Fashion Institute of Technology (FIT) Infor Design and Tech Lab are collaborating on a project aimed at advancing the use of AI in the creative process. Also to prepare the next generation of retail leaders through a high-impact, real-world learning experience as they begin their careers in the $3 trillion apparel industry.
The pilot, which used IBM Research capabilities including computer vision, natural language understanding, and deep learning techniques specifically trained with fashion data. These AI capabilities produced key silhouettes, colours, and a new neural network that designs novel prints and patterns. The FIT students were given access to these IBM Research’s AI tools where they could creatively explore and use 15,000 of Tommy Hilfiger’s product images, some 600,000 publicly available runway images and nearly 100,000 patterns from fabric sites as a source to bring informed inspiration to the student’s design.
The 3D digital designs were presented to PVH and IBM executives, and a Tommy Hilfiger designer who chose a plaid tech jacket by FIT senior Grace McCarty. McCarty incorporated a special thread embedded in a removable, futuristic plaid panel with IBM’s Watson’s Tone Analyzer that responds in near real time to the sentiment in a customer’s social media accounts. When designing her look, she drew inspiration from the AI produced insights on Tommy’s brands’ style and silhouettes, as well as popular and trending colours, and AI generated novel patterns.