Optimal Auction Design in the Joint Advertising

Yang Li, Yuchao Ma, Qi Qi

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 **BundleNet**, a novel bundle-based neural network approach specifically designed for joint advertising. Our extensive experiments demonstrate that the mechanisms generated by **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.

Lay Summary: Online advertising is a vital revenue source for major internet platforms. Recently, joint advertising—placing a bundle of two advertisers in an ad slot instead of allocating a single advertiser —has emerged as an effective way to boost delivery efficiency and revenue. However, existing joint advertising mechanisms focus on individual advertisers while ignoring bundle structure , failing to achieve optimal revenue. Our research first identifies the optimal joint advertising mechanism for single-slot scenarios. For multi-slot scenarios, we propose BundleNet, a novel bundle-based neural network approach specifically designed for joint advertising. Experiments show that BundleNet approximates theoretical optimal solutions in single-slot settings and outperforms state-of-the-art methods in multi-slot settings. It significantly increases platform revenue while ensuring approximate dominant strategy incentive compatibility (to encourage truthful bidding) and individual rationality (to maintain advertiser participation).

Application-Driven Machine Learning: This submission is on Application-Driven Machine Learning.

Primary Area: Applications->Everything Else

Keywords: Joint Advertisement, Auction Design, BundleNet

Submission Number: 11644