HT-GNN: Hyper-Temporal Graph Neural Network for Customer Lifetime Value Prediction in Baidu Ads

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhao, Xiaohui, Zhao, Xinjian, Zhang, Jiahui, Liu, Guoyu, Wang, Houzhi, Wu, Shu
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912832163938304
author Zhao, Xiaohui
Zhao, Xinjian
Zhang, Jiahui
Liu, Guoyu
Wang, Houzhi
Wu, Shu
author_facet Zhao, Xiaohui
Zhao, Xinjian
Zhang, Jiahui
Liu, Guoyu
Wang, Houzhi
Wu, Shu
contents Lifetime value (LTV) prediction is crucial for news feed advertising, enabling platforms to optimize bidding and budget allocation for long-term revenue growth. However, it faces two major challenges: (1) demographic-based targeting creates segment-specific LTV distributions with large value variations across user groups; and (2) dynamic marketing strategies generate irregular behavioral sequences where engagement patterns evolve rapidly. We propose a Hyper-Temporal Graph Neural Network (HT-GNN), which jointly models demographic heterogeneity and temporal dynamics through three key components: (i) a hypergraph-supervised module capturing inter-segment relationships; (ii) a transformer-based temporal encoder with adaptive weighting; and (iii) a task-adaptive mixture-of-experts with dynamic prediction towers for multi-horizon LTV forecasting. Experiments on \textit{Baidu Ads} with 15 million users demonstrate that HT-GNN consistently outperforms state-of-the-art methods across all metrics and prediction horizons.
format Preprint
id arxiv_https___arxiv_org_abs_2601_13013
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HT-GNN: Hyper-Temporal Graph Neural Network for Customer Lifetime Value Prediction in Baidu Ads
Zhao, Xiaohui
Zhao, Xinjian
Zhang, Jiahui
Liu, Guoyu
Wang, Houzhi
Wu, Shu
Machine Learning
Artificial Intelligence
Lifetime value (LTV) prediction is crucial for news feed advertising, enabling platforms to optimize bidding and budget allocation for long-term revenue growth. However, it faces two major challenges: (1) demographic-based targeting creates segment-specific LTV distributions with large value variations across user groups; and (2) dynamic marketing strategies generate irregular behavioral sequences where engagement patterns evolve rapidly. We propose a Hyper-Temporal Graph Neural Network (HT-GNN), which jointly models demographic heterogeneity and temporal dynamics through three key components: (i) a hypergraph-supervised module capturing inter-segment relationships; (ii) a transformer-based temporal encoder with adaptive weighting; and (iii) a task-adaptive mixture-of-experts with dynamic prediction towers for multi-horizon LTV forecasting. Experiments on \textit{Baidu Ads} with 15 million users demonstrate that HT-GNN consistently outperforms state-of-the-art methods across all metrics and prediction horizons.
title HT-GNN: Hyper-Temporal Graph Neural Network for Customer Lifetime Value Prediction in Baidu Ads
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2601.13013