If you've ever opened your favorite app—whether for videos, music, shopping, or beyond—you’ve likely seen multiple rows—or "carousels"—of recommendations: “Keep Watching,” “Just for You,” “Hot Right Now,” and so on. Yet, much of the academic research out there still focuses on a single ranked list—a single column of suggestions. That mismatch between real-world interfaces and research is exactly what inspired us to write “Full-Page Recommender: A Modular Framework for Multi-Carousel Recommendations,” which we will present at RecSys ’25 in Prague later this year.
In this blog post, we’ll walk you through why multi-carousel layouts matter, how our framework tackles the challenge, and what it could mean for the next generation of recommendation experiences (see panels below for a visual example).
Top Picks
Comedies
Recent Releases
Why Carousels?
1. Reflecting Real User Behavior
When platforms use carousels, users naturally scan pages in an F-shaped pattern—glancing at the top carousels before scrolling down or swiping horizontally. By flattening everything into one long list, traditional evaluation methods miss the way people actually browse.
2. Balancing Multiple Goals
A strong carousel page has to juggle different objectives:
- Relevance: Surfacing what a user is most likely to enjoy.
- Diversity: Keeping the page fresh, so it doesn’t feel repetitive.
- Coherence: Ensuring each row sticks to a theme—think “Romantic Comedies” or “Nature Documentaries.”
- Deduplication: Avoiding the same item appearing in multiple rows.
Pushing relevance too hard can hurt diversity; focusing only on diversity might dilute relevance. Our framework seeks a balanced, principled approach.
Our Three-Part, Modular Approach
We break the problem into three pieces, each manageable on its own:
1. Item Ranking.
We start with a standard recommendation model—matrix factorization, autoencoders, or transformers—that assigns each item a “relevance score” for the user.
2. Collection Generation
Next, we group items into coherent “collections.” These could be broad genres (Comedy), niche themes (Heist Movies), or editorial picks. In our experiments, we tried:
- Metadata-based grouping (using tags like “comedy” or “historical”)
- Clustering in an embedding space, so items with similar user-behavior patterns get grouped
- Hybrid, editorially curated lists (e.g., “Editor’s Picks”)
Because items can belong to multiple collections—just like a movie can be both Comedy and Romance—we preserve flexibility.
Carousel Layout Optimization
Finally, we assemble the collections into a vertical list of carousels using a greedy, sequential algorithm. At each step:
- We calculate a combined score for each potential carousel based on item relevance and “freshness” (to avoid duplicates).
- We pick the top-scoring carousel for the next row, then update item freshness (“temperature”) before moving on.
This greedy method approximates a global optimum well enough and runs quickly in real-time.
Measuring Success Beyond Accuracy
Instead of simply flattening everything into one list, we simulate real user behavior:
- F-Shaped Scanning: We weight items based on where they appear on the page, prioritizing the top-left.
- Interest Dynamics: As a simulated user browses, their interest increases when they find relevant items and fades when they don’t.
By converting the page into a “viewing sequence,” we can apply classic metrics like DCG or precision@k in a way that respects layout.
Why This Matters
Shifting from single lists to full-page carousels isn’t just cosmetic. It directly affects:
- Discovery: Improved diversity helps surface unexpected delights.
- Engagement: Better layouts keep users exploring longer.
- Business Metrics: Platforms can showcase new or high-margin items without hurting user satisfaction.
Whether you’re a researcher, product manager, or an avid streamer, understanding this framework sheds light on where recommendation interfaces are headed.
Looking Forward
In the paper, we suggest several next steps:
- Joint Optimization: Planning multiple carousels together instead of one-by-one.
- Automatic Labeling: Leveraging language models to craft catchy, accurate carousel titles.
- Live A/B Testing: Putting these ideas to the test on real platforms.
As multi-carousel layouts become even more prevalent—from video streaming to online shopping—we hope our Full-Page Recommender framework provides a solid foundation for the next wave of discovery engines.
Happy scrolling...