Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Long-term Value Prediction Framework In Video Ranking

Huabin Chen, Xinao Wang, Huiping Chu, Keqin Xu, Chenhao Zhai, Chenyi Wang, Kai Meng, Yuning Jiang

TL;DR

This work proposes a practical ranking-stage LTV framework addressing three challenges: position bias, attribution ambiguity, and temporal limitations, and presents a cross-temporal author modeling module that builds censoring-aware, day-level LTV targets to capture creator-driven re-engagement over longer horizons.

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.

A Long-term Value Prediction Framework In Video Ranking

TL;DR

This work proposes a practical ranking-stage LTV framework addressing three challenges: position bias, attribution ambiguity, and temporal limitations, and presents a cross-temporal author modeling module that builds censoring-aware, day-level LTV targets to capture creator-driven re-engagement over longer horizons.

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.
Paper Structure (17 sections, 13 equations, 8 figures, 6 tables, 2 algorithms)

This paper contains 17 sections, 13 equations, 8 figures, 6 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Works
  3. Immediate Response Prediction
  4. Long-term Value Prediction
  5. Methods
  6. Position Debias Quantile-based Framework
  7. Long-term Value Attribution
  8. Long-term Value Cycle Modeling
  9. Model Framework
  10. Experiments
  11. Experimental Setup
  12. Offline Evaluation
  13. PDQ Method
  14. Attributed Method
  15. Author Time Method
  16. ...and 2 more sections

Figures (8)

  • Figure 1: The framework of LTV prediction.
  • Figure 2: The correlation between slide time and average exposure position over 7 days.
  • Figure 3: The distribution of slide time corresponding to different quantiles under different page groups.
  • Figure 4: The instance of different value attribution types.
  • Figure 5: Percentage Distribution of Slide Time and Attributed Slide Time.
  • ...and 3 more figures