Hierarchically Modeling Micro and Macro Behaviors via Multi-Task Learning for Conversion Rate Prediction

Conversion Rate (\emph{CVR}) prediction in modern industrial e-commerce platforms is becoming increasingly important, which directly contributes to the final revenue. In order to address the well-known sample selection bias (\emph{SSB}) and data sparsity (\emph{DS}) issues encountered during CVR modeling, the abundant labeled macro behaviors (, user's interactions with items) are used. Nonetheless, we observe that several purchase-related micro behaviors (, user's interactions with specific components on the item detail page) can supplement fine-grained cues for \emph{CVR} prediction. Motivated by this observation, we propose a novel \emph{CVR} prediction method by Hierarchically Modeling both Micro and Macro behaviors (). Specifically, we first construct a complete user sequential behavior graph to hierarchically represent micro behaviors and macro behaviors as one-hop and two-hop post-click nodes. Then, we embody as a multi-head deep neural network, which predicts six probability variables corresponding to explicit sub-paths in the graph. They are further combined into the prediction targets of four auxiliary tasks as well as the final according to the conditional probability rule defined on the graph. By employing multi-task learning and leveraging the abundant supervisory labels from micro and macro behaviors, can be trained end-to-end and address the \emph{SSB} and \emph{DS} issues. Extensive experiments on both offline and online settings demonstrate the superiority of the proposed over representative state-of-the-art methods.
View on arXiv