# Multi-Objective Ranking for Live-Streaming: Balancing Fresh and Delayed Signals with Segment-Aware Targeting

arXiv: https://arxiv.org/abs/2608.04455 · HTML: https://mlsanity.com/paper/2608.04455/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 38 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Which Tasks Should Be Learned Together in Multi-task Learning?](https://mlsanity.com/paper/1905.07553/) (2019)
- [Recommendations as Treatments: Debiasing Learning and Evaluation](https://mlsanity.com/paper/1602.05352/) (2016)
- [Bias and Debias in Recommender System: A Survey and Future Directions](https://mlsanity.com/paper/2010.03240/) (2020)
- [Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate](https://mlsanity.com/paper/1804.07931/) (2018)
- [Fairness-Aware Explainable Recommendation over Knowledge Graphs](https://mlsanity.com/paper/2006.02046/) (2020)
- [Unbiased Learning to Rank with Unbiased Propensity Estimation](https://mlsanity.com/paper/1804.05938/) (2018)
- [Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising](https://mlsanity.com/paper/2105.08489/) (2021)
- [Addressing Delayed Feedback for Continuous Training with Neural Networks in CTR prediction](https://mlsanity.com/paper/1907.06558/) (2019)
- [A Nonparametric Delayed Feedback Model for Conversion Rate Prediction](https://mlsanity.com/paper/1802.00255/) (2018)
- [HoME: Hierarchy of Multi-Gate Experts for Multi-Task Learning at Kuaishou](https://mlsanity.com/paper/2408.05430/) (2024)
- [Unbiased Delayed Feedback Label Correction for Conversion Rate Prediction](https://mlsanity.com/paper/2307.12756/) (2023)
- [Multi-Objective Recommendation via Multivariate Policy Learning](https://mlsanity.com/paper/2405.02141/) (2024)
- [Ensure Timeliness and Accuracy: A Novel Sliding Window Data Stream Paradigm for Live Streaming Recommendation](https://mlsanity.com/paper/2402.14399/) (2024)
- [Paragon: Parameter Generation for Controllable Multi-Task Recommendation](https://mlsanity.com/paper/2410.10639/) (2024)
- [OneLive: Dynamically Unified Generative Framework for Live-Streaming Recommendation](https://mlsanity.com/paper/2602.08612/) (2026)
- [Pantheon: Personalized Multi-objective Ensemble Sort via Iterative Pareto Policy Optimization](https://mlsanity.com/paper/2505.13894/) (2025)
- [Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems](https://mlsanity.com/paper/2506.23090/) (2025)
- [Practical Multi-Task Learning for Rare Conversions in Ad Tech](https://mlsanity.com/paper/2507.20161/) (2025)
- [GradCraft: Elevating Multi-task Recommendations through Holistic Gradient Crafting](https://mlsanity.com/paper/2407.19682/) (2024)

## Abstract (arXiv)

One of the most challenging problems entertainment live-streaming services face in recommendation systems is that user behaviors are sparse and delayed, and interaction data exhibits bias for different user segments. Unlike e-commerce applications where user actions follow linear sequences, live-streaming viewers engage in multiple concurrent behaviors of watching, chatting, following, and spending, each occurring with varying delays. We address these challenges through three key contributions: 1) a delayed window approach that extends feedback collection beyond immediate responses, 2) a multi-model architecture that combines fresh and delayed signals, and a segment-aware targeting module that optimizes ranking scores differently across user lifecycle stages, and 3) Multi-gate Mixture-of-Experts (MMoE) integration that jointly models correlated targets while reducing model parameters by 41.9% compared to independent models. Online A/B testing demonstrates significant improvements, including a +0.09% increase in Daily Active Viewers (DAV), generating millions more annual active viewer days, and +0.56% increase in highly engaged viewers' capped Average Revenue Per User (ARPU). Viewer-segment targeting achieved an additional +0.15% DAV improvement for newer and less engaged viewers, while MMoE enhancement added +0.08% overall DAV and +0.27% new follows. The proposed system processes ranking requests with low latency, providing a scalable approach for balancing multiple business objectives across diverse user populations. In addition, we tested the multi-model architecture on the Twitch mobile live feed and achieved a +1.12% increase in positive user-channel interactions (clicks, follows, and likes), demonstrating applicability beyond the primary use case.