Small decisions. Interesting possibilities.Submit contentSubmit

Paper Breakdown research recommendations

Organically integrated JEV in a real project The Paper Breakdown Recommendation Engine We already had a working system that combines content-based and collaborative filtering. Pro users may now get additional curation with Jev. 0.0019$/user for ~70 recs 🤯 ~50 users in 5 secs with concurrent API requests This will cost…

Added to Jevfast

How it uses Jev

Jev adds curation to Paper Breakdown’s existing recommendation engine, which already combines content-based and collaborative filtering. The post describes roughly 70 recommendations per user but not the exact Jev input or how recommendations are combined.

App workflow

  1. Generate existing recommendations

    The engine already combines content-based and collaborative filtering.

  2. Add Jev curation

    Pro users may receive additional recommendations curated with Jev.

  3. Evaluate before rollout

    The creator says they will run quality evaluations before deciding whether to launch the feature.

Why it is interesting

It adds an optional curation stage to an existing recommender, allowing the creator to evaluate the extra layer before rollout.