How eBay is stepping up the use of AI in e-commerce behind the scenes

Low-code and no-code artificial intelligence (AI) tools and immersive 3D visualization usher in the next era of e-commerce.

eBay is leading the way with increased investment in AI-guided experiences, including 3D product renderings to improve shopping experiences and automated listing capabilities to simplify seller tasks.

As one of the world’s largest selling platforms, eBay has been using AI for quite some time — but it’s mostly been done behind the scenes for recommendation systems, fraud detection, and customer intent predictions, explains Stephanie Moyerman, former senior director of risk and trust. science at eBay. She recently transitioned into a new role at Instagram as director of data science wellness.

“What we want to do is integrate [AI] as part of the natural buying and selling experiences and flows,” she told viewers during a livestream this week Transform 2022 event. “We want to bring AI tools to our sellers so that they can provide different, tailored experiences for their buyers without any barrier there.”

Simplifying sales

Most notably, eBay offers 3D product rendering that allows buyers to browse a listing and create a natural browsing experience — as if they were in a brick-and-mortar store, Moyerman said. Low-code and no-code tools allow sellers to scan items with their phone; images are then uploaded to the eBay cloud and converted to a 3D asset.

“They don’t need any professional gear,” said Nitzan Mekel-Bobrov, Chief AI Officer at eBay. All this can be done in minutes and “there is no manual intervention.”

This capability launched in eBay’s sneaker category, with more rolling out to come.

Meanwhile, AI is also being used to enable fast and automated listing capabilities. Sellers can take photos of items and automatically fill lists, reducing the need for manual entries or eliminating the need for them at all.

This capability was initially launched in the trading cards category.

As Mekel-Bobrov explained, these next-generation ecommerce tools are enabled through the use of computer visionimage recognition, convolutional neural networks and fine-grained image analysis.

democratization of AI

Mekel-Bobrov pointed out that eBay sellers are very diverse — ranging from professional brands and large corporations, to mom-and-pops, to occasional sellers, junkers and garage sellers.

AI and low-code and no-code tools open up new possibilities and opportunities in this landscape, while also addressing huge variations when it comes to technical skills, he said.

“We’re a two-sided market,” said Mekel-Bobrov, who said eBay should weigh the needs and wants of both their seller network and their buyers equally. “Our whole raison d’être is to bring sellers and buyers together in that ecommerce context.”

Overcoming challenges

There is no company that develops and applies AI without its challenges, Mekel-Bobrov admitted.

“AI is different from other software applications in a number of ways,” he said. “One of the most important is that AI learns over time.”

This requires continuous feedback loops, where information comes, goes and is stored so that models can be retrained and improved.

In particular, getting AI infrastructure at the scale they want and in real-time requires “huge amounts of infrastructure, both hardware and software,” Mekel-Bobrov said.

And that will grow exponentially with the further democratization of AI.

It boils down to tackling one area at a time – rolling out new capabilities slowly, for example by product categories and subcategories, or by customer segment.

There are also cultural challenges, both internal and external.

Many sellers are not used to such advanced tools; it’s imperative to “help them take it to the next level as the world evolves, as e-commerce evolves,” Mekel-Bobrov said.

With a full-scale metaverse on the horizon is a “new consumer paradigm” emerging and it’s no different from the first arrival of AI, Mekel-Bobrov said.

The parallel, he said, is “talking about it for years and people who don’t know how it’s going to turn out at all and then suddenly it’s there — but it’s not here in a way that people necessarily expected.”

Going forward, eBay’s efforts in AI and low-code and no-code will become “more tactical, more tangible,” he said. This includes doubling AI-guided visual experiences and further integrating them into visual understanding and content understanding. Likewise, eBay will continue to invest in tools – such as more advanced 3D and augmented reality (AR) – and develop cross-platform compatibility.

Meanwhile, the widespread democratization of AI will require more education and investment across the board, Mekel-Bobrov said. He expects the eventual emergence of common standards, best practices and governance. This requires partnership and representation from all companies to ensure the same standards are built and maintained regardless of implementation, he said.

Especially when it comes to the metaverse, e-commerce companies need to work together and take an active role “to make sure it’s shaped in a way that best protects and serves our customers,” said Mekel-Bobrov.

Finally, he said, “I like to talk about the future because you can dream big.”

Watch the full length talk of Transform 2022.