Nantonac Collaborative Filtering : A Model-Based Approach
Nantonac Collaborative Filtering : A Model-Based Approach
复制标题
Nantonac 协同过滤：基于模型的方法
DOI：
10.1145/1864708.1864765
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
T. Kamishima and S. Akaho
中科院分区：
文献类型：
--
作者：
Ikeda;H.;et.al.;T. Kamishima and S. Akaho
推荐系统必须收集用户的偏好数据。为了收集此类数据，已采用使用评级量表（例如好-一般-差或五分制）的评级或评分方法。我们用排序方法取代了这种收集方法，其中对象根据用户的偏好程度进行排序。我们开发了一种基于顺序统计理论将排名转换为分数的技术。该技术成功提高了推荐项目排名的准确性。然而，我们仅针对基于内存的推荐算法。为了测试排名方法和我们的转换技术的使用是否对各种推荐系统有效，我们将我们的转换技术应用于基于模型的算法。
A recommender system has to collect users' preference data. To collect such data, rating or scoring methods that use rating scales, such as good-fair-poor or a five-point-scale, have been employed. We replaced such collection methods with a ranking method, in which objects are sorted according to the degree of a user's preference. We developed a technique to convert the rankings to scores based on order statistics theory. This technique successfully improved the accuracy of ranking recommended items. However, we targeted only memory-based recommendation algorithms. To test whether or not the use of ranking methods and our conversion technique are effective for wide variety of recommenders, we apply our conversion technique to model-based algorithms.