{"ID":2884084,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.07241","arxiv_id":"2508.07241","title":"SocRipple: A Two-Stage Framework for Cold-Start Video Recommendations","abstract":"Most industry scale recommender systems face critical cold start challenges new items lack interaction history, making it difficult to distribute them in a personalized manner. Standard collaborative filtering models underperform due to sparse engagement signals, while content only approaches lack user specific relevance. We propose SocRipple, a novel two stage retrieval framework tailored for coldstart item distribution in social graph based platforms. Stage 1 leverages the creators social connections for targeted initial exposure. Stage 2 builds on early engagement signals and stable user embeddings learned from historical interactions to \"ripple\" outwards via K Nearest Neighbor (KNN) search. Large scale experiments on a major video platform show that SocRipple boosts cold start item distribution by +36% while maintaining user engagement rate on cold start items, effectively balancing new item exposure with personalized recommendations.","short_abstract":"Most industry scale recommender systems face critical cold start challenges new items lack interaction history, making it difficult to distribute them in a personalized manner. Standard collaborative filtering models underperform due to sparse engagement signals, while content only approaches lack user specific relevan...","url_abs":"https://arxiv.org/abs/2508.07241","url_pdf":"https://arxiv.org/pdf/2508.07241v1","authors":"[\"Amit Jaspal\",\"Kapil Dalwani\",\"Ajantha Ramineni\"]","published":"2025-08-10T08:37:36Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\"]","methods":"[]","has_code":false}