English

Modeling Orders of User Behaviors via Differentiable Sorting: A Multi-task Framework to Predicting User Post-click Conversion

Information Retrieval 2023-07-19 v1

Abstract

User post-click conversion prediction is of high interest to researchers and developers. Recent studies employ multi-task learning to tackle the selection bias and data sparsity problem, two severe challenges in post-click behavior prediction, by incorporating click data. However, prior works mainly focused on pointwise learning and the orders of labels (i.e., click and post-click) are not well explored, which naturally poses a listwise learning problem. Inspired by recent advances on differentiable sorting, in this paper, we propose a novel multi-task framework that leverages orders of user behaviors to predict user post-click conversion in an end-to-end approach. Specifically, we define an aggregation operator to combine predicted outputs of different tasks to a unified score, then we use the computed scores to model the label relations via differentiable sorting. Extensive experiments on public and industrial datasets show the superiority of our proposed model against competitive baselines.

Keywords

Cite

@article{arxiv.2307.09089,
  title  = {Modeling Orders of User Behaviors via Differentiable Sorting: A Multi-task Framework to Predicting User Post-click Conversion},
  author = {Menghan Wang and Jinming Yang and Yuchen Guo and Yuming Shen and Mengying Zhu and Yanlin Wang},
  journal= {arXiv preprint arXiv:2307.09089},
  year   = {2023}
}

Comments

The paper is accepted as a short research paper by SIGIR 2023

R2 v1 2026-06-28T11:33:20.986Z