In real-world advertising systems, conversions have different types in nature and ads can be shown in different display scenarios, both of which highly impact the actual conversion rate (CVR). This results in the multi-type and multi-scenario CVR prediction problem. A desired model for this problem should satisfy the following requirements: 1) Accuracy: the model should achieve fine-grained accuracy with respect to any conversion type in any display scenario. 2) Scalability: the model parameter size should be affordable. 3) Convenience: the model should not require a large amount of effort in data partitioning, subset processing and separate storage. Existing approaches cannot simultaneously satisfy these requirements. For example, building a separate model for each (conversion type, display scenario) pair is neither scalable nor convenient. Building a unified model trained on all the data with conversion type and display scenario included as two features is not accurate enough. In this paper, we propose the Masked Multi-domain Network (MMN) to solve this problem. To achieve the accuracy requirement, we model domain-specific parameters and propose a dynamically weighted loss to account for the loss scale imbalance issue within each mini-batch. To achieve the scalability requirement, we propose a parameter sharing and composition strategy to reduce model parameters from a product space to a sum space. To achieve the convenience requirement, we propose an auto-masking strategy which can take mixed data from all the domains as input. It avoids the overhead caused by data partitioning, individual processing and separate storage. Both offline and online experimental results validate the superiority of MMN for multi-type and multi-scenario CVR prediction. MMN is now the serving model for real-time CVR prediction in UC Toutiao.

翻译：在真实世界的广告系统中，转化行为在本质上存在不同类型，广告亦可在不同展示场景中呈现，两者均显著影响实际转化率（CVR），由此产生多类型多场景转化率预测问题。针对该问题的理想模型应满足以下需求：1）准确性：模型需在任意展示场景下针对任意转化类型实现细粒度预测精度；2）可扩展性：模型参数量需在可承受范围内；3）便捷性：模型应避免数据分区、子集处理及独立存储带来的大量工作。现有方法无法同时满足这些需求。例如，为每个（转化类型，展示场景）组合构建独立模型既不可扩展也不便捷；而构建将转化类型与展示场景作为两个特征加入的、基于全部数据训练的统一模型，其精度不足。本文提出掩码多域网络（MMN）来解决该问题。为满足准确性需求，我们建模域特定参数，并提出动态加权损失函数以应对每个小批量内的损失尺度不均衡问题；为满足可扩展性需求，我们提出参数共享与组合策略，将模型参数从乘积空间缩减至求和空间；为满足便捷性需求，我们提出自动掩码策略，该策略可直接接收来自所有域的混合数据作为输入，避免了数据分区、单独处理及独立存储带来的开销。离线和在线实验结果均验证了MMN在多类型多场景CVR预测中的优越性。目前MMN已在UC头条实时CVR预测系统中作为服务模型运行。