ARTIFICIAL INTELLIGENCE TAKES OVER PRODUCT DESIGN & DEVELOPMENT
There is no debate that technology has been disrupting the apparel supply chain, covering manufacturing, sourcing, logistics and even product designing. Brands and retailers have realised the importance of the use of technology in product designing owing to the ever-changing demands of the consumer and also because of the need to speed up the time to market. Based on the report– ‘ The Future of Fashion: From Design to Merchandising, How Tech Is Reshaping the Industry’– by CB Insights, the article explores the disruptions in product designing.
Understanding customers and their needs has been of more importance now than ever before. Fashion brands and retailers across the world are using artificial intelligence to figure out the designs of the future. Data collected from all the platforms are empowering brands to utilise these to predict what customers will want to wear next, with the help of Artificial Intelligence.
Google, the tech giant, has partnered with German retailer Zalando in an experimental project to explore the potential of algorithms in fashion design. Dubbed as ‘Project Muze’, the project uses a neural network trained with the design preferences ( colour, texture, and style) of more than 600 fashion trendsetters along with the features data from the Google Fashion Trend Report, in addition to styles on Zalando. The users, with the help of Project Muze, will be able to create virtual 3D fashion designs on their own.
Amazon is another company that is laying its hands on product design by using the concept of Artificial Intelligence. The company’s research team at Lab126 has developed an algorithm that is capable of learning about a particular fashion style using images. Through a cutting- edge tool known as Generative Adversarial Network ( GAN), the algorithm can generate unique images in similar styles from scratch.
In another development, Amazon is in the process of developing a machine learning algorithm that will be able to decide whether a particular ensemble can be considered as stylish or not. By analysing a few labels attached to the images, the software can provide users with feedback or recommendations for adjustments.
However, AI powered designs need improvement before brands can rely on these algorithms. The outcomes of Google’s Project Muze were just unwearable scrawls and scribbles, while some reports on the Amazon Lab126 initiative called the design results ‘crude’. But surely, these are helping designers make designs in a quick span.
With a proactive approach on AI product designing, even brands are trying to explore the multiple utilities and possibilities. US- based Tommy Hilfiger has joined hands with IBM and the Fashion Institute of Technology for a project that will use IBM AI. These AI tools will help in deciphering real-time fashion industry trends, customer sentiments around Tommy Hilfiger products and runway images and resurfacing themes in trending patterns, silhouettes, colours, and styles. This information can then be used by designers to produce the next collection.
A start- up in USA, ‘Stitch Fix’ is gaining popularity for its AIdriven personalised ensembles for its customers. The company uses algorithms to fetch outfits based on the customers’ favourite colours, patterns, and textiles. These algorithms identify trends and suggest new designs as well based on the information provided by the customers. After the algorithms, human stylists take over to look at the final selection and offer styling suggestions accordingly.
Not only this, Stitch Fix is also using algorithms to actually design new pieces. So far, the initiative, called Hybrid Design, has adopted machine learning to develop over 30 pieces using
A start-up in USA, ‘Stitch Fix’ is gaining popularity for its AI-driven personalised ensembles for its customers. The company uses algorithms to fetch outfits based on the customers’ favourite colours, patterns, and textiles.
this methodology. “We’re uniquely suited to do this,” said Eric Colson, Chief Algorithms Officer at Stitch Fix. “This didn’t exist before because the necessary data didn’t exist. A Nordstrom doesn’t have this type of data because people try things on in the fitting room, and you don’t know what they didn’t buy or why. We now have this access to great data and we can do a lot with it.”
There are independent design platforms also available that allow people to make their own designs. One such platform is CLO that makes it easy to tweak designs on the fly. This means brands can already use real-time AI insights to modify fashion right up to the minute they hit production.
The next era of fashion is all about personalisation and prediction. With more and more data, algorithms will become trend hunters – predicting ( and designing) what’s next in ways that have never been possible.
True Fit, a data- driven personalisation platform for footwear and apparel retailers, uses big data and machine learning for exact-fit clothing and shoe recommendations. With over 56 million registered users, the platform uses transaction data to determine customer preferences that ‘better personalise all touchpoints of the consumer journey’ for brands. Increasingly, consumer preferences will guide every aspect of the design and production process.
The next era of fashion is all about personalisation and prediction. With more and more data, algorithms will become trend hunters – predicting (and designing)