南京大学学报(自然科学版) ›› 2019, Vol. 55 ›› Issue (4): 644–650.doi: 10.13232/j.cnki.jnju.2019.04.014
所属专题： 测试专题
基于动态加权Bagging矩阵分解的推荐系统模型
何轶凡,邹海涛,于化龙(
)
- 江苏科技大学计算机学院，镇江，212003
Recommender system model based on dynamic⁃weighted bagging matrix factorization
Yifan He,Haitao Zou,Hualong Yu()
- School of Computer, Jiangsu University of Science and Technology, Zhenjiang, 212003, China
摘要：
为了提升推荐模型的预测精度，传统方法通常是利用更多的附加信息参与模型的构建.然而，此类方法在提高算法精度的同时也大大增加了算法的时间开销，同时对数据集也存在一定的要求.为了解决上述问题，提出一种基于Bagging集成的矩阵分解模型.该模型根据用户、产品评分数为基学习器动态分配权重，并通过加权求和得到预测评分.在三个不同规模的真实数据集上的实验结果显示：该动态加权Bagging矩阵分解模型拥有与传统矩阵分解模型一样的时间消耗，并且在各个衡量指标上都优于传统的矩阵分解模型.
中图分类号:
- TP391.3
| 1 | ShardanandU,MaesP. Social information filtering：algorithms for automating “Word of Mouth”∥Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. Denver,CO,USA：ACM,1995：210-217. |
| 2 | DeshpandeM,KarypisG. Item?Based Top?N recommendation algorithms. ACM Transactions on Information Systems,2004,22(1)：143-177. |
| 3 | RennieJ D M,SrebroN. Fast maximum margin matrix factorization for collaborative prediction∥Proceedings of The 22th International conference on Machine learning. New York,NY,USA：ACM,2005：713-719. |
| 4 | SalakhutdinovR,MnihA. Probabilistic matrix factorization∥Proceedings of the 20th International Conference on Neural Information Processing Systems. Vancouver,Canada：ACM,2008：1257-1264. |
| 5 | KorenY,BellR,VolinskyC. Matrix factorization techniques for recommender systems. Computer,2009,42(8)：30-37. |
| 6 | ZouH T,GongZ G,ZhangN,et al. Adaptive ensemble with trust networks and collaborative recommendations. Knowledge and Information Systems,2015,44(3)：663-688. |
| 7 | ChengZ Y,DingY,ZhuL,et al. Aspect?aware latent factor model： Rating prediction with ratings and reviews. 2018,arXiv：1802.07938. |
| 8 | ParkD,NeemanJ,ZhangJ,et al. Preference completion：large?scale collaborative ranking from pairwise comparisons∥Proceedings of the 32th International Conference on Machine Learning.Lille,France：Springer,2015：1907-1916. |
| 9 | XuJ W,YaoY,TongH H,et al. HoORaYs：high?order optimization of rating distance for recom?mender systems∥Proceedings of the 23th International Conference on Knowledge Discoveryand Data Mining. Halifax,Canada：ACM,2017：525-534. |
| 10 | WangS,MinkuL L,YaoX. Resampling?based ensemble methods for online class imbalance learning. IEEE Transactions on Knowledge and Data Engineering,2015,27(5)：1356-1368. |
| 11 | SunZ B,SongQ B,ZhuX Y,et al. A novel ensemble method for classifying imbalanced data. Pattern Recognition,2015,48(5)：1623-1637. |
| 12 | 方育柯,傅彦,周俊临. 基于集成学习的个性化推荐算法. 计算机工程与应用,2011,47(10)：1-4. |
| Fang Y K,Fu Y,Zhou J L.Boosting algorithm for personalized recommendation. Computer Engineering and Applications,2011,47(10)：1-4. | |
| 13 |
崔岩,祁伟,庞海龙等. 融合协同过滤和XGBoost的推荐算法. 计算机应用研究,2018,37(1)
doi: 10.19734/j.issn.1001?3695 2018.06.0463 |
|
Cui Y,Qi W,Pang H L,et al. Extreme gradient boosting recommendation algorithm with collaborative filtering. Application Research of Computers,2018,DOI:10.19734/j.issn.1001?3695 2018.06.0463.
doi: 10.19734/j.issn.1001?3695 2018.06.0463 |
|
| 14 | BreimanL. Bagging predictors. Machine Learning,1996,24(2)：123-140. |
| 15 | OhJ,HanW S,YuH,et al. Fast and robust parallel SGD matrix factorization∥Proceedings of the 21th International Conference on Knowledge Discovery and Data Mining. Sydney,Australia：ACM,2015：865-874. |
| 16 | JohnsonR W. An introduction to the bootstrap. Teaching Statistics,2001,23(2)：49-54. |
| [1] | 徐媛媛,张恒汝,闵帆,黄雨婷. 三支交互推荐[J]. 南京大学学报(自然科学版), 2019, 55(6): 973-983. |
| [2] | 宗林林，张宪超*，赵乾利，于 红，刘馨月. 一种多流形正则化的多视图非负矩阵分解算法[J]. 南京大学学报(自然科学版), 2017, 53(3): 557-. |
| [3] | 卢文凯*，景丽萍*，杨 柳 . 截断式鲁棒非负矩阵分解算法[J]. 南京大学学报(自然科学版), 2016, 52(4): 714-. |
| [4] | 张燕平1,2张顺1,2钱付兰1,2严远亭1,2. 一种局部和全局用户影响力相结合的社交推荐算法[J]. 南京大学学报(自然科学版), 2015, 51(4): 858-865. |
| [5] | 韦素云1**，业宁1，吉根林2，张丹丹1，殷晓飞1 . 基于项目类别和兴趣度的协同过滤推荐算法*[J]. 南京大学学报(自然科学版), 2013, 49(2): 142-149. |
|