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

TL;DR

This paper introduces HT-GNN, a novel hyper-temporal graph neural network designed to improve customer lifetime value prediction in Baidu Ads by modeling demographic heterogeneity and dynamic behavioral sequences.

Contribution

The paper presents a new HT-GNN model that combines hypergraph structures, transformer-based temporal encoding, and mixture-of-experts for multi-horizon LTV prediction, addressing key challenges in advertising.

Findings

HT-GNN outperforms existing methods across all metrics.

The model effectively captures demographic and temporal variations.

Experiments on 15 million users validate its scalability and accuracy.

Abstract

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.