Adaptive Bid Shading Optimization of First-Price Ad Inventory
Adaptive Bid Shading Optimization of First-Price Ad Inventory
复制标题
一价广告库存的自适应出价阴影优化
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Qian Sang
中科院分区：
文献类型：
--
作者：
N. Karlsson;Qian Sang
反馈控制和分散式优化在在线程序化广告系统中已经变得越来越重要，来处理活动预算调整和性能优化。这些解决方案通常涉及基于拍卖的广告库存分配，这在历史上是使用第二价格成本模型实现的。近年来，该行业已迅速过渡到主要的第一价格成本模式。这对广告商的最优投标策略有重要的影响。特别是，投标必须有阴影（折扣），以避免多付。本文提出了一种自适应方案的在线学习的最佳出价着色。该方案涉及分割，一个双参数的非线性着色机制，和参数优化的在线学习算法。该学习算法采用递归最小二乘估计的盈余和参数之间的关系的对数二次模型，和牛顿式梯度下降更新计划，以找到盈余最大化的阴影参数。在Verizon媒体需求侧平台（DSP）上的实验结果表明了该方法的有效性。
Feedback control and decentralized optimization have become increasingly important in online programmatic advertising systems, e.g., to deal with campaign budget pacing and performance optimization. The solutions typically involve an auction-based allocation of ad inventory, which historically was implemented using a second-price cost model. In recent years the industry has rapidly transitioned to predominantly a first-price cost model. This has important implications on what is the optimal bidding strategy for advertisers. In particular, bids have to be shaded (discounted) to avoid overpaying. This paper proposes an adaptive scheme for online learning of optimal bid shading. The scheme involves segmentation, a two-parametric nonlinear shading mechanism, and an online learning algorithm for parameter optimization. The learning algorithm employs a recursive least squares estimation of a log-quadratic model of the relationship between the surplus and the parameters, and a Newton-like gradient descent update scheme to find the surplus maximizing shading parameters. The effectiveness of the proposed approach is demonstrated with experiment results from Verizon Media Demand Side Platform (DSP).