Apple · Apple Machine Learning
Personalizing Incremental Video Search with Hybrid Text and ID Embeddings
Compiled by KHAO Editorial — aggregated from 1 source + 2 references discovered via search. See llms.txt for citation guidance.
✓ KHAO Verified
Personalizing Incremental Video Search with Hybrid Text and ID Embeddings.
Key facts
- Offline, for sessions with user history, the personalized ranker improves NDCG@10 by 2.99% and MRR by 3.30% over the non-personalized baseline
- Online, treatment yields statistically significant gains of +1.14% tap-through rate and +1.23% conversion rate, with a 2.91% improvement in converted-item rank position
- Crucially, slice analyses show that personalization is most needed in incremental search, where intent is still forming: on ambiguous prefix queries (1–3 characters), NDCG@10 lift is +8.63%, versus
- Users with longer watch histories benefit more from personalization than newer users: NDCG lift rises from +2.13% for users with 1–5 history items to +4.37% for users with 51–100
Summary
Authors Vivek Kanojiya, Vishalaksh Aggarwal, Daeho Baek, Lyndon Kennedy, Xuetao Yin. Incremental video search requires high-quality ranking after each keystroke, where intent is often underspecified (e.g., 1–3 character prefixes). Offline, for sessions with user history, the personalized ranker improves NDCG@10 by 2.99% and MRR by 3.30% over the non-personalized baseline. Users with longer watch histories benefit more from personalization than newer users: NDCG lift rises from +2.13% for users with 1–5 history items to +4.37% for users with 51–100. This larger lift occurs even though baseline relevance is lower for long-history cohorts (NDCG@10 drops from 0.733 to 0.680), indicating that personalization adds the most value where default ranking underperforms.