HMAF: A Hierarchical Multi-Slot GD-RTB Allocation Framework

2026-06-04

AI Summary

This work addresses the challenge of jointly optimizing guaranteed delivery (GD) and real-time bidding (RTB) in multi-ad-slot scenarios, where existing approaches struggle to balance long-term contractual obligations with short-term revenue maximization. To this end, the authors propose the HMAF framework, which formulates GD–RTB coordination as a hierarchical multi-slot allocation problem for the first time. HMAF employs a three-stage Plan–Calibrate–Execute paradigm that integrates offline integer programming, online dynamic calibration, and list-wise ranking algorithms to enable efficient real-time decision-making under complex constraints. Deployed across multiple marketing platforms at Meituan, the framework demonstrates significant practical impact, improving GD fulfillment rates by 3.72% and increasing total ad revenue by 1.59%.

Abstract

In modern online advertising platforms, Guaranteed Delivery (GD) contracts coexist and bid with Real-Time Bidding (RTB) auctions. Recent approaches either decouple GD and RTB optimization or rely on heuristic priority rules, and thus fail to effectively balance short-term revenue maximization with long-term contract delivery under complex multi-slot delivery and impression constraints. To address these challenges, we propose HMAF (Hierarchical Multi-Slot Allocation Framework), a unified framework designed to optimize impression allocation in GD--RTB advertising platforms. HMAF employs the Plan--Calibrate--Execute paradigm as its core structure, and integrates offline constraint optimization with online decision-making, balancing offline GD resource planning, dynamically calibrating GD--RTB competitiveness, and making real-time listwise rank decisions across multi-slot environments. HMAF has been implemented in multiple marketing scenarios at Meituan, one of the world's largest online food delivery platforms, leading to a 3.72% increase in GD delivery rate and a 1.59% increase in total advertisement revenue.

Problem

• Guaranteed Delivery
• Real-Time Bidding
• multi-slot allocation
• impression constraints
• advertising platforms

Innovation

• Hierarchical Multi-Slot Allocation
• Guaranteed Delivery
• Real-Time Bidding
• Plan-Calibrate-Execute Paradigm
• Listwise Ranking