Bosca / Recommendations

Bosca Recommendations

The right content,
for each person,
as they arrive.

Bosca Recommendations generates candidates with strategies you tune, then ranks them live for each viewer — blending behavior, meaning, and cohort. It works on brand-new content from day one, and learns from every gesture.

How it works

Generate broadly. Rank personally.

The work splits in two: building candidate pools is global and shared; ranking them is personal and live. That's what keeps personalization fresh without precomputing a feed for everyone.

01

Strategies generate candidates

Strategies build pools of candidates in the background — what's trending, what people engaged with together — with no per-person targeting. That work is shared across everyone.

02

Serving ranks them live

When a person opens a feed, the platform ranks the candidates for that viewer on the spot — blending the model's scores, their ratings, and what they've hidden. Only people who ask for a feed pay for it.

03

Feedback tunes it

A gesture — boost, lower, care, or hide — feeds straight back into the next ranking, so the feed keeps adjusting to what each person actually wants.

What makes it powerful

More than "most popular." Personal.

A production recommender — cold-start, multi-signal ranking, quality gates, and experimentation — wired into the same content, profiles, and events as the rest of the platform.

Live personalization

Feeds are ranked on demand, not precomputed for every profile in a batch. Ranking, rating-based re-ranking, and dismissal filtering all run at request time — so only the people who ask for a feed cost anything to serve.

Cold-start on day one

New content is recommendable immediately. A model that learns from a piece's own features and meaning surfaces it before it has a single interaction.

Many signals, one feed

Behavioral co-engagement, semantic similarity, and cohort personalization merge into a single ranked set — and every result can explain which signal put it there.

Learns from feedback

Boost, lower, care, and hide gestures become ratings and dismissals that steer the next ranking. High ratings even become durable learned interests.

People like you

Co-engagement can be conditioned on a viewer's cohort — a deterministic key built from the signals you define — so a feed aligns to people who behave alike.

Quality gates

A newly trained model has to measure up to the one in service on held-out data before it can take over; per-placement score floors and diversity caps keep low-confidence and repetitive results out.

Built-in A/B testing

Provision an experiment to pit the model against a heuristic, or a new model against the current one — split by a feature flag, with a safe default if anything is off.

A test console

Try every surface live from Studio against any profile or item — feeds, trending, similar, co-engagement — each result tagged with its score, strategy, and reason.

Serving surfaces

One engine, many surfaces

Every surface is a query on the same recommendation engine — a feed, a "related" row, a "people also viewed" strip — so you place the right one wherever it belongs.

For You

forYou

A person's personalized feed, ranked live from the trained model.

Placement

placement

Recommendations for a named spot in your app, assembled from its strategies.

Recommended

recommended

The "related content" surface — behavioral and content signals merged, re-ranked for the viewer.

Similar

similar

Content alike in meaning, from the content model's item-to-item index.

Co-engaged

coEngaged

"People who engaged with this also engaged with" — item-to-item behavior.

Trending

trending

Globally trending content by recent interaction velocity.

Recommendations ship with Bosca

The recommender learns from the same content, profiles, and events every other subsystem produces — no pipeline to build, no data to ship out. The docs cover strategies, placements, signals, and the model end to end.