in ,

Roland Simon: Pixyle AI is on a mission to transform the way people discover products online by helping retailers build better search with visual AI

Follow Roland Simon

Pixyle AI is on a mission to transform the way people discover products online by helping retailers build better search with visual AI.

Pixyle AI provides image recognition solutions for fashion retailers, enabling them to improve efficiency in catalogue management, deliver a better online shopping experience and boost e-commerce sales.

The team is based between offices in Amsterdam and North-Macedonia and works with retailers all over the world including Depop (UK), Otrium (Netherlands) and Miinto (Denmark).

Tell us about yourself?

I have a background in marketing at corporates (Ex-L’Oréal and AholDDelhaize). I started advising startups and had a great click with the founder of, Svetlana Kordumova.

While she has a more technical background (she has a phd in AI and computer vision) I have a more commercial background, which is very complementary.

After working together for over a year, she asked me to come on board as a co-founder, which I happily accepted.

What is the inspiration behind your business?

As a PhD student at the University of Amsterdam graduating in AI and computer vision, Svetlana couldn’t believe how tedious and frustrating the process of online shopping was.

Pixyle AI originated from not being able to find the clothes that she was looking for, while knowing that there was advanced image search technology available to make it so much easier. She set out to transform the way people shop online and help them find what they want with ease.

In 2018, Pixyle was founded as a visual search app for consumers. The company pivoted early in 2019 to B2B as we discovered that we could make much more impact selling our image recognition technology to brands & retailers.

We now serve retail clients across the world, helping them improve their site search & product discovery through product data enrichment, powered by visual AI.

Today, search engines and site search are failing shoppers owing to inconsistent, incomplete and inaccurate data quality linked to products that isn’t helping them find what they are looking for. Research shows that 94% of searches deliver irrelevant results and 72% of sites completely fall short of search expectations.

As a result, the majority of shoppers abandon their search and they’re not coming back. Google has estimated (in the US alone) the cost of such bad search experiences is $300B in lost revenue each year.

At Pixyle AI, we automatically enrich data by extracting detailed attributes from images. Our product data enrichment platform helps brands & retailers connect their shoppers with products they’re really looking for.

What is your magic sauce?

We’ve developed an extensive fashion taxonomy (more than 20,000 attributes, and ever-growing) that captures the intent of every possible search query. Simply put, our automatically generated rich attributes fuel a retailer’s site search engine and makes it perform better.

Richer data improves product discoverability and ultimately, increases conversions and boosts sales. Our clients have experienced up to 10% conversion rate increases and millions in revenue lift.

What we believe sets us apart from the competition, is that we are laser focused on data enrichment with detailed attribution, and to provide the best value for our clients, we offer a level of customization and tagging flexibility that is unheard of in the industry.

In order to make product data enrichment really work for each specific situation of our clients, we first let our teams align on what we’re trying to achieve, and make sure to set the right configurations before our AI models get to work.

This means that we map taxonomies, configure cloud architectures and deploy customer and technical support teams to the exact needs of our customers, ensuring a successful implementation and usage of our platform to help them achieve long-term business goals.

Where do you see your company going in 5 years?

We envision to become the leader in product data enrichment in ecommerce, helping brands and retailers deliver better search and discovery experiences. Therefor, we will:

  • 1. Enhance our product offering
  • 2. Move into new verticals, with homeware & furniture on the roadmap for this year
  • 3. Further expand our geographic reach beyond Europe

What has been your biggest setback so far?

The war on talent; more difficult than expected to find the right people that fit our needs and our culture

What is the next big challenge for your business?

We just raised our €1M seed round. This allows us to invest in our product and scale our team. I consider hiring a big challenge. Recruiting the right people with the right skills who fit our amazing company culture – while at the same time keeping tabs on our running the business.

How do people get involved/buy into your vision?

We’re developing the world’s most accurate visual AI-enabled product data enrichment platform for ecommerce. Developers and data scientists who are excited about the prospect of building this advanced technology with us, are welcome to apply at

Follow on Linkedin and Twitter

Written by Fredd

Leave a Reply

Your email address will not be published. Required fields are marked *

GIPHY App Key not set. Please check settings

Photo by Markus Spiske on Unsplash

Technology Being Used To Analyse Statistics Within The NBA And The Finals

(France)  Emil Novakov: Scaleflex simplifies the upload, management, optimization and delivery of media assets online.