In this article, we present our approach to personalizing Etsy Ads through encoding and learning from short-term (one-hour) sequences of user actions and diverse representations. To this end we introduce a three-component adSformer diversifiable personalization module (ADPM) and illustrate how we use this module to derive a short-term dynamic user representation and personalize the Click-Through Rate (CTR) and Post-Click Conversion Rate (PCCVR) models used in sponsored search (ad) ranking. The first component of the ADPM is a custom transformer encoder that learns the inherent structure from the sequence of actions. ADPM's second component enriches the signal through visual, multimodal and textual pretrained representations. Lastly, the third ADPM component includes a "learned" on the fly average pooled representation. The ADPM-personalized CTR and PCCVR models, henceforth referred to as adSformer CTR and adSformer PCCVR, outperform the CTR and PCCVR production baselines by $+6.65\%$ and $+12.70\%$, respectively, in offline Precision-Recall Area Under the Curve (PR AUC). At the time of this writing, following the online gains in A/B tests, such as $+5.34\%$ in return on ad spend, a seller success metric, we are ramping up the adSformers to $100\%$ traffic in Etsy Ads.

翻译：本文提出了通过编码和学习用户行为的短期（一小时）序列及多样化表征来实现Etsy广告个性化的方法。为此，我们引入了一个三组件adSformer可多样化个性化模块（ADPM），并阐述如何利用该模块推导短期动态用户表征，进而对搜索广告排序中使用的点击率（CTR）和点击后转化率（PCCVR）模型进行个性化。ADPM的第一组件是自定义Transformer编码器，用于学习行为序列的内在结构；第二组件通过视觉、多模态和文本预训练表征丰富信号；第三组件包含一种“在线学习”的均值池化表征。经ADPM个性化的CTR和PCCVR模型（以下称adSformer CTR和adSformer PCCVR）在离线精确率-召回率曲线下面积（PR AUC）上分别以$+6.65\%$和$+12.70\%$的优势超越生产环境基线模型。截至目前，基于A/B测试的线上收益（如卖家成功指标广告支出回报率提升$+5.34\%$），我们正将adSformer模型逐步扩展至Etsy广告的$100\%$流量中。