A Novel Personalized Recommendation Algorithm of Collaborative Filtering Based on RFM Model
In order to improve the accuracy of recommendation, especially the matrix score of personalized recommendation technology is too spars, a new recommendation algorithm was proposed. The advantages of this algorithm were mainly embodied in the following aspects. Firstly, the improved algorithm with RF...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2015-09-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2015180/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841529581892272128 |
|---|---|
| author | Ning Zhang Chongrui Fan Yan Zhang |
| author_facet | Ning Zhang Chongrui Fan Yan Zhang |
| author_sort | Ning Zhang |
| collection | DOAJ |
| description | In order to improve the accuracy of recommendation, especially the matrix score of personalized recommendation technology is too spars, a new recommendation algorithm was proposed. The advantages of this algorithm were mainly embodied in the following aspects. Firstly, the improved algorithm with RFM model was used to select the original customer in some condition, making the recommended source of data more accurate and efficient. Secondly, in the improved algorithm the customer consumption history records were filled to the matrix to improve the consistency of the matrix of score. Thirdly, the traditional Pearson similarity calculation formula was improved to make the search of target users of similar neighbor more accurate. Then the simulation experiment was carried on by using the improved algorithm. It can be proved that the improved algorithm is better than the traditional one in accuracy. At last, the improved algorithm was applied to a recommendation system with personalized recommendation function. It was shown that the recommendation algorithm was efficient and valid. |
| format | Article |
| id | doaj-art-052d8ac391e34dcb8df613fd06995be4 |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2015-09-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-052d8ac391e34dcb8df613fd06995be42025-01-15T03:16:39ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012015-09-013110311159613652A Novel Personalized Recommendation Algorithm of Collaborative Filtering Based on RFM ModelNing ZhangChongrui FanYan ZhangIn order to improve the accuracy of recommendation, especially the matrix score of personalized recommendation technology is too spars, a new recommendation algorithm was proposed. The advantages of this algorithm were mainly embodied in the following aspects. Firstly, the improved algorithm with RFM model was used to select the original customer in some condition, making the recommended source of data more accurate and efficient. Secondly, in the improved algorithm the customer consumption history records were filled to the matrix to improve the consistency of the matrix of score. Thirdly, the traditional Pearson similarity calculation formula was improved to make the search of target users of similar neighbor more accurate. Then the simulation experiment was carried on by using the improved algorithm. It can be proved that the improved algorithm is better than the traditional one in accuracy. At last, the improved algorithm was applied to a recommendation system with personalized recommendation function. It was shown that the recommendation algorithm was efficient and valid.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2015180/personalized recommendationcollaborative filteringscore matrix |
| spellingShingle | Ning Zhang Chongrui Fan Yan Zhang A Novel Personalized Recommendation Algorithm of Collaborative Filtering Based on RFM Model Dianxin kexue personalized recommendation collaborative filtering score matrix |
| title | A Novel Personalized Recommendation Algorithm of Collaborative Filtering Based on RFM Model |
| title_full | A Novel Personalized Recommendation Algorithm of Collaborative Filtering Based on RFM Model |
| title_fullStr | A Novel Personalized Recommendation Algorithm of Collaborative Filtering Based on RFM Model |
| title_full_unstemmed | A Novel Personalized Recommendation Algorithm of Collaborative Filtering Based on RFM Model |
| title_short | A Novel Personalized Recommendation Algorithm of Collaborative Filtering Based on RFM Model |
| title_sort | novel personalized recommendation algorithm of collaborative filtering based on rfm model |
| topic | personalized recommendation collaborative filtering score matrix |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2015180/ |
| work_keys_str_mv | AT ningzhang anovelpersonalizedrecommendationalgorithmofcollaborativefilteringbasedonrfmmodel AT chongruifan anovelpersonalizedrecommendationalgorithmofcollaborativefilteringbasedonrfmmodel AT yanzhang anovelpersonalizedrecommendationalgorithmofcollaborativefilteringbasedonrfmmodel AT ningzhang novelpersonalizedrecommendationalgorithmofcollaborativefilteringbasedonrfmmodel AT chongruifan novelpersonalizedrecommendationalgorithmofcollaborativefilteringbasedonrfmmodel AT yanzhang novelpersonalizedrecommendationalgorithmofcollaborativefilteringbasedonrfmmodel |