Myntra
, the online fashion retailer, has partnered with
Microsoft
to bring generative
AI
to its shopping app, introducing a new chatbot with a knack for fashion. Powered by Microsoft’s
Azure OpenAI
service, the chatbot called
MyFashionGPT
enables users to search products using natural language rather than just keywords .
The company says that the feature frees users from the constraints of traditional searches that rely on matching specific keywords already present in a product catalogue.
MyFashionGPT can comprehend open-ended queries like "suggest me clothes for a beach trip" and returns relevant items from various categories, including beachwear, hats, sunglasses, and more.
The AI assistant integrated seamlessly with existing Azure infrastructure, accelerating deployment. “Myntra’s systems are on Azure and deploying Azure
OpenAI
Service was as seamless as deploying another server and it gave us a secure way of using generative AI,” said Vindhya Priya Shanmugam, director of engineering at Myntra.
Mnytra’s team was pleasantly surprised by how
ChatGPT
could synthesise natural language prompts. The team then tried to ask various questions over two days to see what they could achieve. They were surprised to find that ChatGPT was able to answer questions like what clothes to wear for regional festivals like Pongal and Onam. They asked about the look of an actor from a recent movie and could describe it accurately. The team even tried to search in Hindi with "sardiyon ke kapde" which translates to "winter clothes" in English, and ChatGPT understood it.
MyFashionGPT was launched in May, during the End of Reason Sale. Users can access MyFashionGPT by clicking on the icon located to the right of the search bar on Myntra's app. They can use the chatbot to search for specific requirements or outfit queries based on occasions, travel locations, popular events, and even celebrity looks from popular movies.
The company says that MyFashionGPT has changed the way people search and shop on the platform since its launch. The AI assistant deciphers the intent behind imprecise search strings and offers fresh product discovery options, expanding the scope of queries and streamlining the search process.
“Users who shop using the AI shopping assistant are three times more likely to end up making a purchase,” said Arit Mondal, director of product management at Myntra. “Because it also helps users discover a complete look from multiple categories of products, we’re seeing that on average they add products from 16 per cent more categories than usual.”
Myntra plans to use generative AI to build a feature, which could be able to complete outfits by selecting tops, bottoms, and accessories. Additionally, the company plans to add voice search and personalization to the chatbot in the future.