A Long-term Value Prediction Framework In Video Ranking

TL;DR

This paper introduces a comprehensive long-term value prediction framework for video ranking that addresses position bias, attribution ambiguity, and temporal limitations, improving long-term engagement metrics in large-scale systems.

Contribution

It presents novel modules for position bias normalization, nuanced attribution learning, and cross-temporal modeling, enabling effective long-term value estimation in billion-scale video recommendation systems.

Findings

Significant improvements in LTV metrics observed in offline and online tests.

Framework deployed at billion-scale in Taobao, enhancing engagement.

Supports efficient training and deployment within industrial constraints.

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.