基于协同过滤的个性化图书推荐系统研究

在许多应用领域，多标准推荐系统使用多标准决策方法实施推荐，但是，多标准推荐系统在实施和测试方面仍然相当有限，特别是在一些特定领域，文中提出了三种多标准功效协同过滤算法的几种设计方案的实验分析，使用的数据集是模拟产生的，实验的目的是为了证实当来自于真实用户的多标准评估数据集不能得到的时候，如何产生数据集，并用于实施研究和选择一个恰当的算法。一个来自数字图书馆图书推荐的实例用于说明算法的使用，验证其有效性。

Research on personalized book recommendation system based on collaborative filtering techniques

Recommender systems have already been engaging multiple criteria for me proaucuon oxrecommendations. Multi-criteriar ecommenders apply multi-criteria decision making methods to facilitaterecommendation in numerous application domains. On the other hand, systematic implementation andtesting of multi-criteria recommender systems in the context of real-life applications still remain ratherlimited. In this paper, the experimental analysis of several design options for three pattribute utility collaborative filtering algorithms is presented. The data set used is synthetic, with multi-criteria evaluations that have been created using an appropriate simulation environment. The aim of theexperiment is to demonstrate how a synthetic data set may be created and used to facilitate the study andselection of an appropriate recommendation algorithm, when multi-criteria evaluations from real users arenot available. A example from digital library study is used to illustrate the usage of the proposedalgorithm. The experimental resuh demonstrate the effective of the proposed algorithm.