Paper
A Long-term Value Prediction Framework In Video Ranking
Authors
Huabin Chen, Xinao Wang, Huiping Chu, Keqin Xu, Chenhao Zhai, Chenyi Wang, Kai Meng, Yuning Jiang
Abstract
Accurately modeling long-term value (LTV) at the ranking stage of short-video recommendation remains challenging. While delayed feedback and extended engagement have been explored, fine-grained attribution and robust position normalization at billion-scale are still underdeveloped. We propose a practical ranking-stage LTV framework addressing three challenges: position bias, attribution ambiguity, and temporal limitations. (1) Position bias: We introduce a Position-aware Debias Quantile (PDQ) module that normalizes engagement via quantile-based distributions, enabling position-robust LTV estimation without architectural changes. (2) Attribution ambiguity: We propose a multi-dimensional attribution module that learns continuous attribution strengths across contextual, behavioral, and content signals, replacing static rules to capture nuanced inter-video influence. A customized hybrid loss with explicit noise filtering improves causal clarity. (3) Temporal limitations: We present a cross-temporal author modeling module that builds censoring-aware, day-level LTV targets to capture creator-driven re-engagement over longer horizons; the design is extensible to other dimensions (e.g., topics, styles). Offline studies and online A/B tests show significant improvements in LTV metrics and stable trade-offs with short-term objectives. Implemented as task augmentation within an existing ranking model, the framework supports efficient training and serving, and has been deployed at billion-scale in Taobao's production system, delivering sustained engagement gains while remaining compatible with industrial constraints.
Metadata
Related papers
Fractal universe and quantum gravity made simple
Fabio Briscese, Gianluca Calcagni • 2026-03-25
POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan
Marta Moscati, Muhammad Saad Saeed, Marina Zanoni, Mubashir Noman, Rohan Kuma... • 2026-03-25
LensWalk: Agentic Video Understanding by Planning How You See in Videos
Keliang Li, Yansong Li, Hongze Shen, Mengdi Liu, Hong Chang, Shiguang Shan • 2026-03-25
Orientation Reconstruction of Proteins using Coulomb Explosions
Tomas André, Alfredo Bellisario, Nicusor Timneanu, Carl Caleman • 2026-03-25
The role of spatial context and multitask learning in the detection of organic and conventional farming systems based on Sentinel-2 time series
Jan Hemmerling, Marcel Schwieder, Philippe Rufin, Leon-Friedrich Thomas, Mire... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2602.17058v1</id>\n <title>A Long-term Value Prediction Framework In Video Ranking</title>\n <updated>2026-02-19T04:01:01Z</updated>\n <link href='https://arxiv.org/abs/2602.17058v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2602.17058v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Accurately modeling long-term value (LTV) at the ranking stage of short-video recommendation remains challenging. While delayed feedback and extended engagement have been explored, fine-grained attribution and robust position normalization at billion-scale are still underdeveloped. We propose a practical ranking-stage LTV framework addressing three challenges: position bias, attribution ambiguity, and temporal limitations.\n (1) Position bias: We introduce a Position-aware Debias Quantile (PDQ) module that normalizes engagement via quantile-based distributions, enabling position-robust LTV estimation without architectural changes. (2) Attribution ambiguity: We propose a multi-dimensional attribution module that learns continuous attribution strengths across contextual, behavioral, and content signals, replacing static rules to capture nuanced inter-video influence. A customized hybrid loss with explicit noise filtering improves causal clarity. (3) Temporal limitations: We present a cross-temporal author modeling module that builds censoring-aware, day-level LTV targets to capture creator-driven re-engagement over longer horizons; the design is extensible to other dimensions (e.g., topics, styles).\n Offline studies and online A/B tests show significant improvements in LTV metrics and stable trade-offs with short-term objectives. Implemented as task augmentation within an existing ranking model, the framework supports efficient training and serving, and has been deployed at billion-scale in Taobao's production system, delivering sustained engagement gains while remaining compatible with industrial constraints.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.IR'/>\n <published>2026-02-19T04:01:01Z</published>\n <arxiv:comment>9 pages</arxiv:comment>\n <arxiv:primary_category term='cs.IR'/>\n <author>\n <name>Huabin Chen</name>\n </author>\n <author>\n <name>Xinao Wang</name>\n </author>\n <author>\n <name>Huiping Chu</name>\n </author>\n <author>\n <name>Keqin Xu</name>\n </author>\n <author>\n <name>Chenhao Zhai</name>\n </author>\n <author>\n <name>Chenyi Wang</name>\n </author>\n <author>\n <name>Kai Meng</name>\n </author>\n <author>\n <name>Yuning Jiang</name>\n </author>\n <arxiv:doi>10.1145/3774904.3792830</arxiv:doi>\n <link href='https://doi.org/10.1145/3774904.3792830' rel='related' title='doi'/>\n </entry>"
}