• Macedonian startup Pixyle AI secures €1 million in capital to help fashion e-commerce deliver better search experiences.
• The seed round is led by South Central Ventures.
• The Pixyle AI solution generates detailed and accurate product attributes, allowing consumers to get to the items they want faster.
Visual AI startup for e-commerce, Pixyl AI is on a mission to connect retailers’ online audiences with the products they are actually looking to buy.
Consumers’ poor product discovery experience costs online sellers and e-commerce businesses billions of dollars because they fail to meet user expectations. Pixyle AI’s solution aims to help them solve this problem.
Research watch that 94% of searches return irrelevant results and that 72% of sites completely fail to meet search expectations. As a result, the majority of buyers abandon their search and do not return.
Founded in 2018 by Svetlana Kordumova, who holds a PhD in AI and computer vision from the University of Amsterdam, the Macedonian startup helps fashion retailers with image recognition solutions, enabling them to offer better online shopping experience, boost online sales and improve their efficiency. in catalog management with intelligent capture of product data.
Visual AI finds the location of fashion items in images, determines the category of the item i.e. dress, sneaker, etc., then Pixyle AI digs deeper into the image to classify attributes i.e. color, pattern etc. in the language used by buyers.
“For example, in e-commerce, when site visitors search for a specific product to purchase and type in “short summer dress with floral print in purple and pink” and this type of dress is shown to customers, in the catalog. they should be labeled with the length “short”, the occasion “summer”, with a pattern “floral” and the colors “purple” and “pink”. It starts with building the right taxonomy. Having the right metadata associated with product images helps retailers capture everyday popular search queries as well as long-tail searches,” Kordumova said in a statement.
The AI solution also enhances product data and improves the relevance of search results for product discovery, leading to higher conversion rates. Tags generated by Pixyle AI can be easily absorbed into a retailer’s existing e-commerce stack, allowing its search and discovery platform to operate seamlessly and faster, the company said.
Recruit talent across the region and expand into new verticals
According to Jan Kobler of South Central Ventures, Pixyle AI’s solution has already been tested in the market and the company is now ready to scale.
“Product research is an essential part of engaging online shoppers: being able to find what you want easily and quickly. However, search has been extremely underserved and remains an unmet need for retailers and buyers to date. Pixyle AI is focused on this opportunity and is already making a difference by increasing sales for retailers. They have built a robust technology stack, which has been proven and tested in the market and is ready to scale. We look forward to working with the founders and helping them grow their business in the years to come,” Kobler said in a statement.
The startup, which has offices in the Netherlands and North Macedonia, will now use the new funds to hire talent in the Western Balkans region.
“We will use the funds to hire talented people in the Western Balkans who want to join us in our journey to become the leading product data enrichment platform for e-commerce. We will expand our offering with exciting new AI products and offer suites that will help fashion brands and retailers operate more efficiently, improve site search and increase conversions,” Kordumova told The Recursive .
In addition, Pixyle AI will also focus on launching a new product using object character recognition (OCR) technology that allows its customers to recognize brands, material composition, size and country original “made in” from a label in a fashion product. article.
“In addition to markup, we will also provide auto-generated, SEO-optimized product descriptions. As for new verticals, we plan to launch into homewares and furniture by the end of 2023, and two other verticals by the end of 2024: beauty and electronics. Kordumova concluded.