In the age of big data, recommendation systems provide users with fast access to interesting information, resulting to a significant commercial value. However, the extreme sparseness of user assessment data is one of the key factors that lead to the poor performance of recommendation algorithms. To address this problem, we propose a spectral clustering recommendation scheme with low-rank matrix completion and spectral clustering. Our scheme exploits spectral clustering to achieve the division of a similar user group. Meanwhile, the low-rank matrix completion is used to effectively predict un-rated items in the sub-matrix of the spectral clustering. With the real dataset experiment, the results show that our proposed scheme can effectively improve the prediction accuracy of un-rated items.
Qian WANG
AnHui University of Technology
Qingmei ZHOU
AnHui University of Technology
Wei ZHAO
AnHui University of Technology
Xuangou WU
AnHui University of Technology
Xun SHAO
Kitami Institute of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Qian WANG, Qingmei ZHOU, Wei ZHAO, Xuangou WU, Xun SHAO, "Top-N Recommendation Using Low-Rank Matrix Completion and Spectral Clustering" in IEICE TRANSACTIONS on Communications,
vol. E103-B, no. 9, pp. 951-959, September 2020, doi: 10.1587/transcom.2019EBP3230.
Abstract: In the age of big data, recommendation systems provide users with fast access to interesting information, resulting to a significant commercial value. However, the extreme sparseness of user assessment data is one of the key factors that lead to the poor performance of recommendation algorithms. To address this problem, we propose a spectral clustering recommendation scheme with low-rank matrix completion and spectral clustering. Our scheme exploits spectral clustering to achieve the division of a similar user group. Meanwhile, the low-rank matrix completion is used to effectively predict un-rated items in the sub-matrix of the spectral clustering. With the real dataset experiment, the results show that our proposed scheme can effectively improve the prediction accuracy of un-rated items.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2019EBP3230/_p
Copy
@ARTICLE{e103-b_9_951,
author={Qian WANG, Qingmei ZHOU, Wei ZHAO, Xuangou WU, Xun SHAO, },
journal={IEICE TRANSACTIONS on Communications},
title={Top-N Recommendation Using Low-Rank Matrix Completion and Spectral Clustering},
year={2020},
volume={E103-B},
number={9},
pages={951-959},
abstract={In the age of big data, recommendation systems provide users with fast access to interesting information, resulting to a significant commercial value. However, the extreme sparseness of user assessment data is one of the key factors that lead to the poor performance of recommendation algorithms. To address this problem, we propose a spectral clustering recommendation scheme with low-rank matrix completion and spectral clustering. Our scheme exploits spectral clustering to achieve the division of a similar user group. Meanwhile, the low-rank matrix completion is used to effectively predict un-rated items in the sub-matrix of the spectral clustering. With the real dataset experiment, the results show that our proposed scheme can effectively improve the prediction accuracy of un-rated items.},
keywords={},
doi={10.1587/transcom.2019EBP3230},
ISSN={1745-1345},
month={September},}
Copy
TY - JOUR
TI - Top-N Recommendation Using Low-Rank Matrix Completion and Spectral Clustering
T2 - IEICE TRANSACTIONS on Communications
SP - 951
EP - 959
AU - Qian WANG
AU - Qingmei ZHOU
AU - Wei ZHAO
AU - Xuangou WU
AU - Xun SHAO
PY - 2020
DO - 10.1587/transcom.2019EBP3230
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E103-B
IS - 9
JA - IEICE TRANSACTIONS on Communications
Y1 - September 2020
AB - In the age of big data, recommendation systems provide users with fast access to interesting information, resulting to a significant commercial value. However, the extreme sparseness of user assessment data is one of the key factors that lead to the poor performance of recommendation algorithms. To address this problem, we propose a spectral clustering recommendation scheme with low-rank matrix completion and spectral clustering. Our scheme exploits spectral clustering to achieve the division of a similar user group. Meanwhile, the low-rank matrix completion is used to effectively predict un-rated items in the sub-matrix of the spectral clustering. With the real dataset experiment, the results show that our proposed scheme can effectively improve the prediction accuracy of un-rated items.
ER -