论文标题
通过基于树的方法在广告预测中通过基于树的方法生成自动历史特征
Automatic Historical Feature Generation through Tree-based Method in Ads Prediction
论文作者
论文摘要
历史功能在广告点击率（CTR）预测中很重要，因为它们解释了用户和广告之间的过去参与。在本文中，我们研究了如何通过计数特征有效地构建历史特征。这种问题的关键挑战在于如何自动识别计数密钥。我们提出了一种基于树的方法来计算密钥选择。直觉是，决策树自然提供了各种功能组合，可以用作计数关键候选者。为了选择个性化计数功能，我们每个用户都会训练一个决策树模型，并且以基于频率的重要性度量的不同用户选择计数键。为了验证拟议解决方案的有效性，我们在Twitter视频广告数据上进行了大规模实验。在在线学习和离线培训设置中，自动确定的计数功能优于手动策划的计数功能。
Historical features are important in ads click-through rate (CTR) prediction, because they account for past engagements between users and ads. In this paper, we study how to efficiently construct historical features through counting features. The key challenge of such problem lies in how to automatically identify counting keys. We propose a tree-based method for counting key selection. The intuition is that a decision tree naturally provides various combinations of features, which could be used as counting key candidate. In order to select personalized counting features, we train one decision tree model per user, and the counting keys are selected across different users with a frequency-based importance measure. To validate the effectiveness of proposed solution, we conduct large scale experiments on Twitter video advertising data. In both online learning and offline training settings, the automatically identified counting features outperform the manually curated counting features.
