Understanding item consumption orders for right-order next-item recommendation
Understanding item consumption orders for right-order next-item recommendation
复制标题
DOI：
10.1007/s10115-017-1122-5
复制
发表时间：
2017-10
影响因子：
2.7
通讯作者：
Jun Chen;Xuecheng Wang;Chaokun Wang
中科院分区：
文献类型：
--
作者：
Jun Chen;Xuecheng Wang;Chaokun Wang
尽管推荐系统中的相关性问题已经得到了很好的研究，推荐系统中的相关性问题，通常指的是用户的偏好与系统推荐的项目之间的相似性，但以前几乎没有提到以正确的顺序进行推荐的问题。订单定义了物品之间应该更好地消费的方式。对真实世界数据集的分析表明，物品的消费模式在有序程度上很强。在本文中，我们提出了一种新的方法来解决正确的订单推荐问题，该方法基于包含商品消费订单的图结构。该方法可以将相关性和排序效应结合在一起。我们尝试推荐用户会话中连续步骤中的相关项目，以便用户在连续步骤中选择的项目可以按正确的顺序串在一起。在三个真实数据集上进行的实验评估表明，与基准推荐方法相比，考虑物品消费顺序的推荐方法的推荐准确率有所提高。此外，对正确顺序推荐的研究不仅有助于对推荐适当性的探讨，也有助于对推荐适当性的探讨。
Although the relevance problem in recommender systems, which typically refers to the similarity between the preference of the user and the items the system recommends, has been well studied, the issue of making recommendations in right orders has barely been mentioned before. The order defines the way in which items should be better consumed in relation to each other. The analysis of real-world data sets demonstrates strong item consumption patterns in the degree of order. In this paper, we propose a novel method to tackle the right-order recommendation problem based on a graph structure that incorporates the item consumption orders. The proposed method can combine relevance and order effects in recommendations. We attempt to recommend the relevant items in the consecutive steps within a user session so that the user’s selected items in the consecutive steps can be stringed together in a right order. The experimental evaluation conducted on three real-world data sets shows that the recommendation accuracy is improved by considering item consumption orders compared with the baseline recommendation methods. In addition, the study on right-order recommendation contributes to the exploration on recommendation appropriateness besides relevance.