arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.07907cs.IR
收藏

AIE:面向在线广告点击率预测的拍卖信息增强框架

AIE: Auction Information Enhanced Framework for CTR Prediction in Online Advertising

Yang Yang, Bo Chen, Chenxu Zhu, Menghui Zhu, Xinyi Dai, Huifeng Guo, Muyu Zhang, Zhenhua Dong, Ruiming Tang

AI总结:

针对现有CTR预测未充分利用拍卖信息且存在拍卖偏差的问题,提出含两个轻量可插拔模块的AIE框架,经多数据集实验和线上A/B测试验证,有效提升eCPM与CTR指标。

摘要:

点击率(CTR)预测是在线广告推荐的核心技术,而复杂的线上竞价拍卖流程也给CTR优化带来了诸多难题。已有研究表明,引入后验拍卖信息有助于提升CTR预测的性能,但现有工作未能充分利用拍卖信息的价值,且忽略了拍卖带来的数据偏差,导致结果存在偏差且未达最优。为解决这些局限,我们提出了面向在线广告CTR预测的拍卖信息增强框架(Auction Information Enhanced Framework,AIE),该框架深入探究了拍卖信号利用不足的问题,并首次揭示了拍卖偏差问题。具体而言,AIE引入了两个可插拔模块,分别是自适应市场价辅助模块(Adaptive Market-price Auxiliary Module,AM2)和出价校准模块(Bid Calibration Module,BCM),二者协同工作以更好地挖掘后验拍卖信号,提升CTR预测性能。此外,所提出的两个模块均为轻量级、模型无关的,且对推理延迟友好。我们在一个公开数据集和一个工业数据集上开展了大量实验,验证了AIE的有效性和兼容性。此外,在某大型广告平台开展的为期一个月的线上A/B测试显示,AIE使基础模型的有效千次展示收益(eCPM)和CTR分别提升了5.76%和2.44%。

英文摘要:

Click-Through Rate (CTR) prediction is a fundamental technique for online advertising recommendation and the complex online competitive auction process also brings many difficulties to CTR optimization. Recent studies have shown that introducing posterior auction information contributes to the performance of CTR prediction. However, existing work doesn't fully capitalize on the benefits of auction information and overlooks the data bias brought by the auction, leading to biased and suboptimal results. To address these limitations, we propose Auction Information Enhanced Framework (AIE) for CTR prediction in online advertising, which delves into the problem of insufficient utilization of auction signals and first reveals the auction bias. Specifically, AIE introduces two pluggable modules, namely Adaptive Market-price Auxiliary Module (AM2) and Bid Calibration Module (BCM), which work collaboratively to excavate the posterior auction signals better and enhance the performance of CTR prediction. Furthermore, the two proposed modules are lightweight, model-agnostic, and friendly to inference latency. Extensive experiments are conducted on a public dataset and an industrial dataset to demonstrate the effectiveness and compatibility of AIE. Besides, a one-month online A/B test in a large-scale advertising platform shows that AIE improves the base model by 5.76% and 2.44% in terms of eCPM and CTR, respectively.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑