A multi-model ranking framework that separates fresh and delayed signals, adds viewer-segment weighting, and uses MMoE improves Twitch recommendation metrics in online A/B tests.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-Objective Ranking for Live-Streaming: Balancing Fresh and Delayed Signals with Segment-Aware Targeting
A multi-model ranking framework that separates fresh and delayed signals, adds viewer-segment weighting, and uses MMoE improves Twitch recommendation metrics in online A/B tests.