Wallapop has struck a strategic partnership with Swiss AI company Albatross to roll out real-time, in-session product discovery across its second-hand marketplace. It expects the move to lift user engagement and improve the visibility of sellers’ listings.
The deployment shifts Wallapop away from recommendation tools that rely mainly on a user’s past behaviour and item popularity. Instead, it uses signals from a user’s actions during a browsing session and updates results as those actions change.
Wallapop operates a consumer-to-consumer marketplace focused on reused goods. Founded in Barcelona, it now operates in Spain, Italy and Portugal. The company says it has 21 million monthly users who generate more than 100 million listings a year across categories including consumer goods and motor vehicles.
Albatross, founded in Switzerland in 2024, sells software that analyses sequences of user interactions to adjust discovery and search. It says its systems orchestrate discovery across more than 100 million products and process billions of user interactions.
How It Works
Traditional marketplace recommenders tend to show more of what a user has already viewed, or what is popular with others. The new system focuses on real-time intent within a session, adjusting the items presented as a shopper moves from one product type to another.
One example involves a user viewing a second-hand sofa and then moving to rugs or floor lamps. In that scenario, the system interprets a shift from evaluating one item to furnishing a room, and highlights related items across categories rather than continuing to surface more sofas.
In another example, a shopper clicks on a vintage coffee table after browsing other items. The system can then start showing items such as lighting, paintings, décor or storage pieces that match a style, even if the user has not searched for them directly.
Test Results
Wallapop and Albatross reported early results from a four-week A/B test on 10% of Wallapop’s traffic, measuring performance across the homepage experience.
They reported a 118.9% increase in user engagement and a 104.8% increase in favourites and interactions. Purchase intentions rose by 46.9%, according to the figures.
The companies said the system surfaced previously unseen items to “qualified buyers”, suggesting it can broaden exposure beyond already popular listings.
They also said the gains remained stable and continued to improve over a four-month production period, positioning the results as extending beyond short-term testing and novelty effects.
Seller Visibility
For marketplaces built on unique, one-off items, seller visibility is a recurring challenge. Listings often have inconsistent or incomplete metadata, and many items have low or no engagement history, especially shortly after posting.
In that context, matching live buyer intent to relevant, shippable listings could change how quickly items move and which sellers gain attention. The partnership introduces what the companies call “algorithmic seller discovery”, aimed at ensuring quality supply is not lost in volume.
ReCommerce platforms also face rapid catalogue turnover as items sell and new listings replace them. Real-time session signals can respond faster than models that depend on long historical patterns, particularly for niche items with limited comparison points.
“At Wallapop, we are moving toward a system that understands what users want in real time, helping buyers find the right items faster while giving sellers more effective visibility for their listings,” said Rob Cassedy, CEO of Wallapop. “Our collaboration with Albatross represents another step forward in our mission to empower people to participate in a more conscious consumption model that creates economic opportunities for people.”
Funding Context
The partnership follows Albatross’ recent USD $12.25 million fundraise, which it linked to the rollout of what it calls a real-time “perception layer”. Albatross positions its work as focused on discovery in environments where users face a large number of choices.
“Together with Wallapop, we’re delivering an online discovery experience comparable to the best in-store journey; one where users uncover products that feel like true hidden gems, tailored just for them, in real time,” said Dr. Kevin Kahn, CEO of Albatross AI. “While large language models make sense of words, Albatross’ perception model makes sense of the sequence and context of user actions as they happen. This partnership demonstrates a radical shift in discovery, search, and personalization, which have seen little innovation for more than a decade.”
The companies described the Wallapop rollout as an early large-scale commercial deployment of adaptive, in-session discovery for reCommerce. Further work is expected as the system expands across the marketplace and processes a wider range of user sessions and listing categories.