文献类型：期刊文献

英文题名：An improved ridge regression algorithm and its application in predicting TV ratings

作者：Ma, Nan[1];Zhao, Sicheng[2];Sun, Zhen[3];Wu, Xiuping[1];Zhai, Yun[4]

第一作者：马楠

通讯作者：Zhao, SC[1]

机构：[1]Beijing Union Univ, Coll Robot, Beijing 100101, Peoples R China;[2]Tsinghua Univ, Sch Software, Beijing 100084, Peoples R China;[3]Beijing Union Univ, Coll Informat Technol, Beijing 100101, Peoples R China;[4]Chinese Acad Governance, E Govt Res Ctr, Beijincpg 100089, Peoples R China

第一机构：北京联合大学机器人学院

通讯机构：[1]corresponding author), Tsinghua Univ, Sch Software, Beijing 100084, Peoples R China.

年份：2019

卷号：78

期号：1

起止页码：525-536

外文期刊名：MULTIMEDIA TOOLS AND APPLICATIONS

收录：;EI(收录号：20174104257905);Scopus(收录号：2-s2.0-85030711270);WOS:【SCI-EXPANDED(收录号:WOS:000457317500029)】；

基金：This work is supported by the National Natural Science Foundation of China (Nos. 61672178, 61601458, 61701273 and 91420202) and the Project Funded by China Postdoctoral Science Foundation (No. 2017 M610897). The authors would also like to thank the anonymous reviewers for their constructive suggestions to improve the paper.

语种：英文

外文关键词：Ridge regression; Least Square method; TV ratings

摘要：U Ridge regression is a biased estimated regressive method, which is traditionally used in collinearity data analysis. It is actually a modified Least Square method, which gains more rational and reliable regression coefficient by giving up the unbiasedness of Least Squares Estimation, reducing partial information and decreasing accuracy to overcome the over-fitting problems. This article presents an improved ridge regression algorithm and utilizes it to predict the audience rating for TV ratings. It is tested by 10 - fold Cross Validation. TV rating is an important indication to measure the quality and user experience, as well as one of the vital standards to state the value of a TV channel. The improved ridge regression algorithm is used to learn the model of weight matrix, which is trained by the error algorithm to predict the TV ratings. The extensive experimental results demonstrate the effectiveness of the proposed algorithm.