arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.02771cs.IRcs.LG
收藏

PURS:提高用户满意度的个性化意外推荐系统

PURS: Personalized Unexpected Recommender System for Improving User Satisfaction

New York University(纽约大学);Alibaba Youku Cognitive and Intelligent Lab(阿里巴巴优酷认知与智能实验室)

Pan Li, Maofei Que, Zhichao Jiang, Yao Hu, Alexander Tuzhilin

摘要:

经典的推荐系统方法通常面临过滤气泡问题,当用户只收到他们熟悉的项目的建议,使他们感到无聊和不满。为了解决过滤器气泡问题,已经提出了意想不到的推荐,以推荐显著偏离用户先前期望的项目,从而通过向用户呈现“新鲜的”和先前未探索的项目来使他们惊讶。在本文中,我们描述了一种新的个性化意外推荐系统(PURS)模型,将意外的推荐过程中,通过提供多聚类建模的用户兴趣的潜在空间和个性化的意外通过自我注意力机制和通过选择一个适当的意外激活函数。在三个真实世界数据集上进行的大量离线实验表明,所提出的PURS模型在准确性和意外性测量方面都显着优于最先进的基线方法。此外,我们在主要视频平台阿里巴巴-优酷进行了在线A/B测试,我们的模型在每个用户的平均视频观看量指标上实现了超过3%的增长。该公司正在部署拟议的模式。

英文摘要:

Classical recommender system methods typically face the filter bubble problem when users only receive recommendations of their familiar items, making them bored and dissatisfied. To address the filter bubble problem, unexpected recommendations have been proposed to recommend items significantly deviating from user's prior expectations and thus surprising them by presenting "fresh" and previously unexplored items to the users. In this paper, we describe a novel Personalized Unexpected Recommender System (PURS) model that incorporates unexpectedness into the recommendation process by providing multi-cluster modeling of user interests in the latent space and personalized unexpectedness via the self-attention mechanism and via selection of an appropriate unexpected activation function. Extensive offline experiments on three real-world datasets illustrate that the proposed PURS model significantly outperforms the state-of-the-art baseline approaches in terms of both accuracy and unexpectedness measures. In addition, we conduct an online A/B test at a major video platform Alibaba-Youku, where our model achieves over 3\% increase in the average video view per user metric. The proposed model is in the process of being deployed by the company.

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。

↑