arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1902.04743cs.IR
收藏

基于会话的循环神经网络顺序跳转预测

Session-based Sequential Skip Prediction via Recurrent Neural Networks

Lin Zhu, Yihong Chen

摘要:

WSDM Cup 2019的重点是基于会话的顺序跳过预测,即预测用户是否会跳过曲目,考虑到他们在收听会话中的前一次交互。本文提供了我们的团队\textbf{ekffar}的解决方案,以应对这一挑战。我们专注于基于递归神经网络的深度学习方法,这些方法在基于会话的推荐问题上表现良好。我们表明,通过选择适当的递归架构,适当地考虑到给定的信息,如用户交互功能和歌曲元数据,一个单一的神经网络可以实现平均平均精度(AA)得分为0.648的保留测试数据。同时,通过集成核心模型的几个变体,可以进一步提高整体推荐准确性。通过使用所提出的方法,我们的团队能够在比赛中获得第一名。我们已经在GitHub上开源了我们的实现。

英文摘要:

The focus of WSDM cup 2019 is session-based sequential skip prediction, i.e. predicting whether users will skip tracks, given their immediately preceding interactions in their listening session. This paper provides the solution of our team \textbf{ekffar} to this challenge. We focus on recurrent-neural-network-based deep learning approaches which have previously been shown to perform well on session-based recommendation problems. We show that by choosing an appropriate recurrent architecture that properly accounts for the given information such as user interaction features and song metadata, a single neural network could achieve a Mean Average Accuracy (AA) score of 0.648 on the withheld test data. Meanwhile, by ensembling several variants of the core model, the overall recommendation accuracy can be improved even further. By using the proposed approach, our team was able to attain the 1st place in the competition. We have open-sourced our implementation at GitHub.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑