Optimal Auction Design in the Joint Advertising

TL;DR

This paper develops an optimal auction mechanism for joint advertising, introducing a neural network approach called BundleNet that improves revenue and incentive compatibility in multi-slot settings.

Contribution

It presents the first optimal mechanism for single-slot joint advertising and introduces BundleNet, a neural network for multi-slot joint advertising, achieving near-optimal revenue.

Findings

Mechanisms approximate theoretical results in single-slot setting.

BundleNet achieves state-of-the-art performance in multi-slot advertising.

Significant revenue increase with incentive compatibility and individual rationality.

Abstract

Online advertising is a vital revenue source for major internet platforms. Recently, joint advertising, which assigns a bundle of two advertisers in an ad slot instead of allocating a single advertiser, has emerged as an effective method for enhancing allocation efficiency and revenue. However, existing mechanisms for joint advertising fail to realize the optimality, as they tend to focus on individual advertisers and overlook bundle structures. This paper identifies an optimal mechanism for joint advertising in a single-slot setting. For multi-slot joint advertising, we propose \textbf{BundleNet}, a novel bundle-based neural network approach specifically designed for joint advertising. Our extensive experiments demonstrate that the mechanisms generated by \textbf{BundleNet} approximate the theoretical analysis results in the single-slot setting and achieve state-of-the-art performance in the multi-slot setting. This significantly increases platform revenue while ensuring approximate dominant strategy incentive compatibility and individual rationality.