Abstract:

Currently， the most common way to predict Click-Through Rate （CTR） is to extract interest features through feature interaction techniques， but most of these methods ignore the inherent relationships between users and items， and fail to fully explore the potential interests of users implied among items. To address this problem， a Personalized Multi-layer Interest extraction Click-through rate prediction model （PMIC） was proposed， aiming to mine multi-layer interests shown by users at the same time from different perspectives. Firstly， the recall matching method was employed to learn and model the relationships between users and items from both the item learning module and the user learning module， thereby capturing diverse interests of users. Secondly， the multi-head self-attention mechanism was utilized within the item learning module to concurrently extract multiple potential interests. Finally， a corresponding inner product method was adopted to further refine and enhance the feature representation between users and items. Experimental results on multiple public datasets demonstrate that PMIC improves the Area Under the receiver operating characteristic Curve （AUC） by at least 2.3%.

Key words: e-commerce, deep learning, Click-Through Rate (CTR) prediction, multi-head self-attention mechanism, Multi-Layer Perceptron (MLP)

摘要：

目前，点击率（CTR）预测最常用的方法是利用特征交互技术提取兴趣特征，但这些方法大多忽视了用户与项目之间的内在联系，同时也未能充分发掘项目间所蕴含的用户潜在兴趣。针对该问题，提出一种个性化多层兴趣提取点击率预测模型（PMIC），旨在从不同角度深入挖掘用户在同一时间内展现的多层兴趣。首先，采用召回匹配的方法，从项目学习模块和用户学习模块两个角度学习并建模用户与项目之间的联系，捕捉用户多样化的兴趣；其次，利用多头自注意力机制，在项目学习模块中提取同一时间内隐含的多个潜在兴趣；最后，通过内积计算，进一步细化和加强用户与项目之间的特征表达。在多个公共数据集上的实验结果表明，与基线模型相比，PMIC的受试者特征工作曲线下面积（AUC）最少提高了2.3%。

关键词: 电子商务, 深度学习, 点击率预测, 多头自注意力机制, 多层感知机