Research on Recommendation Algorithm of Matrix Factorization Method Based on MapReduce

Hui Xia

doi:10.4028/www.scientific.net/AMM.631-632.138

Paper Titles

Adaptive Extended Kalman Filter for Nonlinear System with Noise Compensating Technology
p.121

An Improvement of Apriori Algorithm in Medical Data Mining
p.125

An Integrated Algorithm for Low-Carbon City Evaluation Based on Neural Network and Analytic Hierarchy Process
p.129

Reliability Optimization for Multi-State Series-Parallel System Design Using Ant Colony Algorithm
p.133

Research on Recommendation Algorithm of Matrix Factorization Method Based on MapReduce
p.138

Research on the Characteristic of Social Information Ground’s Spatial Structure and Information Dynamics
p.142

Review of Regional Power Grid Fault Information Screening
p.147

Single-Step Optimal Design for a Class of Nonlinear Singular System and Epidemic Control
p.153

Trust Calculation Model in Knowledge Community
p.161

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 631-632Research on Recommendation Algorithm of Matrix...

Research on Recommendation Algorithm of Matrix Factorization Method Based on MapReduce

Abstract:

Matrix factorization is a collaborative filtering recommendation technique proposed in recent years.In the process of recommendation,each prediction depends on the collaboration of the whole known rating set and the feature matrices need huge storage. So the recommendation with only one node will meet the bottleneck of time and resource. A MapReduce-based matrix factorization recommendation algorithm was proposed to solve this problem.The big feature matrices were shared by Hadoop distributed cache and MapFile techniques.The MapReduce algorithm could also handle multi-λsituation.The experiment on Netflix data set shows that the MapReduce-based algorithm has high speedup and improves the efficiency of collaborative filtering.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 631-632)

Pages:

138-141

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.631-632.138

Citation:

Cite this paper

Online since:

September 2014

Authors:

Hui Xia*

Keywords:

Collaborative Filtering Recommendation, Hadoop, MapReduce, Matrix Factorization

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Hailin Xu, XiaoWu, Xiaodong Li. Comparative study of Internet recommendation technology[J]. Journal of Software, 2009，20(2)：350—362.

Google Scholar

[2] Koren Y, Bell R. Volinsky C. Matrix Factorization Techniques for Recommender Systems[J]. Computer，2009, 42(8): 30-37.

DOI: 10.1109/mc.2009.263

Google Scholar

[3] Bell R M，Koren Y．Scalable Collaborative Filtering with Jointly Derived Neighborhood Interpolation Weights[C]/Proc of the 7th IEEE International Conference on Data Mining. Omaha NE, USA：IEEE，2007: 43-52.

DOI: 10.1109/icdm.2007.90

Google Scholar

[4] Takacs G，Pilaszy I，Nemeth B，et a1．Matrix Factorization and Neighbor Based Algorithms the Netflix Prize Problem[c]∥Proceedings of the 2008 ACM conference on Recommender systems. Lausanne, Switzerland: ACM, 2008: 267-274.

DOI: 10.1145/1454008.1454049

Google Scholar

[5] P. Shi, E. K. Boukas and R. K. Agarwal, H1 control of discrete-time linear uncertain systems with delayed-state, Proc. of 37th IEEE Conference on Decision & Control, Tampa, Florida, pp.4551-4552, (1998).

DOI: 10.1109/cdc.1998.762043

Google Scholar

[6] Zhou Y，Wilkinson D，Schreiber R, et a1. Large-Scale Parallel Collaborative Filtering for the Netflix Prize[C]f{Proc of the 4th international conference on Algorithmic Aspects in Information and Management．(2008).

DOI: 10.1007/978-3-540-68880-8_32

Google Scholar

[7] Dean J, Ghemawat s. MapReduce: Simplified Data Processing on Large Clusters[J]. Communication of the ACM 50tlI anniversary issue，2008，51(1)：107-113.

DOI: 10.1145/1327452.1327492

Google Scholar