欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
在电子商务中,协同推荐技术能够帮助用户发现感兴趣的东西。在协同推荐中,通常采用最近邻居的方法来产生推荐。随着商品数量的增多,协同推荐所需要的数据集也越来越稀疏,可用数据比例越来越少。为了解决这个问题,本文在传统的评分数据的基础上,引入用户的基本信息,对用户的基本信息进行离散化处理,将用户的基本信息转化成一个0、1的向量,然后将用户的评分矩阵转变成0、1矩阵并与用户的基本信息进行组合形成一个新的矩阵,对这个扩展的矩阵用奇异矩阵分解（SVD）降维,然后在SVD分解出的矩阵U和S的基础上计算最近邻居,并预测用户对项目的预测评分。实验表明引入用户的基本信息,并采用对基本信息离散化的处理方式,能够提高预测评分的准确性。
英文摘要：
In the e-commerce business,collaborative recommendation technology can help people find something that are interested to them.In collaborative recommendation,there is a common way to generate recommendation called nearest neighbor method.With the increase of commodity quantity,the ratio of useful data is decreasing.In order to solve this problem,in this paper,on the basis of ordinary score data,we import the user information,discretize user information,convert user information to a 0,1 vector,convert the score matrix to a 0,1 matrix and assemble then to a new matrix.We employ the singular value decompositions method to reduce the dimensionality,use the U and S matrix to compute nearest neighbors,and predict the items＇ score.The experiment results show that by importing the user information,discretizing the user information,this method can improve the predicting score precision.
同期刊论文项目
同项目期刊论文
Web-oriented OOV translation extracting approach through cross-language query expansion for English-
BioPPISVMExtractor:A Protein-Protein Interaction Extractor for Biomedical Literature Using SVM and R
Uncertainty sampling-based active learning for protein-protein interaction extraction from biomedica
Improving the performance of bio-entity name recognition in biomedical literature via the contextual
Incorporating rich features to boost information retrieval performance: A SVM-regression based re-ra
位置：