Collaborative filtering and deep learning based hybrid recommendation for cold start problem

Jian Wei; Jianhua He; Kai Chen; Yi Zhou; Zuoyin Tang

doi:10.1109/DASC-PICom-DataCom-CyberSciTec.2016.149

Collaborative filtering and deep learning based hybrid recommendation for cold start problem

Jian Wei, Jianhua He, Kai Chen (Lead / Corresponding author), Yi Zhou, Zuoyin Tang

Research output: Chapter in Book/Report/Conference proceeding › Chapter

45 Citations (Scopus)

555 Downloads (Pure)

Abstract

Recommender systems (RS) are used by many social networking applications and online e-commercial services. Collaborative filtering (CF) is one of the most popular approaches used for RS. However traditional CF approach suffers from sparsity and cold start problems. In this paper, we propose a hybrid recommendation model to address the cold start problem, which explores the item content features learned from a deep learning neural network and applies them to the timeSVD++ CF model. Extensive experiments are run on a large Netflix rating dataset for movies. Experiment results show that the proposed hybrid recommendation model provides a good prediction for cold start items, and performs better than four existing recommendation models for rating of non-cold start items.

Original language	English
Title of host publication	Proceedings - 2016 IEEE Cyber Science and Technology Congress (CyberSciTech 2016), 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing (DASC 2016), 2016 IEEE 14th International Conference on Pervasive Intelligence and Com
Editors	Randall Bilof
Place of Publication	Piscataway
Publisher	IEEE
Pages	874-877
Number of pages	4
ISBN (Electronic)	9781509040650
ISBN (Print)	9781509040667
DOIs	https://doi.org/10.1109/DASC-PICom-DataCom-CyberSciTec.2016.149
Publication status	Published - 13 Oct 2016

Keywords

collaboration
computational modeling
data models
machine learning
motion pictures
predictive models
training
Computer Vision and Pattern Recognition
Information Systems
Computer Science (miscellaneous)
Artificial Intelligence
Computer Networks and Communications

Access to Document

10.1109/DASC-PICom-DataCom-CyberSciTec.2016.149

Author Accepted Manuscript
© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 2.82 MB

Cite this

Wei, J., He, J., Chen, K., Zhou, Y., & Tang, Z. (2016). Collaborative filtering and deep learning based hybrid recommendation for cold start problem. In R. Bilof (Ed.), Proceedings - 2016 IEEE Cyber Science and Technology Congress (CyberSciTech 2016), 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing (DASC 2016), 2016 IEEE 14th International Conference on Pervasive Intelligence and Com (pp. 874-877). IEEE. https://doi.org/10.1109/DASC-PICom-DataCom-CyberSciTec.2016.149

Wei, Jian ; He, Jianhua ; Chen, Kai et al. / Collaborative filtering and deep learning based hybrid recommendation for cold start problem. Proceedings - 2016 IEEE Cyber Science and Technology Congress (CyberSciTech 2016), 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing (DASC 2016), 2016 IEEE 14th International Conference on Pervasive Intelligence and Com. editor / Randall Bilof. Piscataway : IEEE, 2016. pp. 874-877

@inbook{0fa2b9c4f8084ea5b97efae20f5ba373,

title = "Collaborative filtering and deep learning based hybrid recommendation for cold start problem",

abstract = "Recommender systems (RS) are used by many social networking applications and online e-commercial services. Collaborative filtering (CF) is one of the most popular approaches used for RS. However traditional CF approach suffers from sparsity and cold start problems. In this paper, we propose a hybrid recommendation model to address the cold start problem, which explores the item content features learned from a deep learning neural network and applies them to the timeSVD++ CF model. Extensive experiments are run on a large Netflix rating dataset for movies. Experiment results show that the proposed hybrid recommendation model provides a good prediction for cold start items, and performs better than four existing recommendation models for rating of non-cold start items.",

keywords = "collaboration, computational modeling, data models, machine learning, motion pictures, predictive models, training, Computer Vision and Pattern Recognition, Information Systems, Computer Science (miscellaneous), Artificial Intelligence, Computer Networks and Communications",

author = "Jian Wei and Jianhua He and Kai Chen and Yi Zhou and Zuoyin Tang",

year = "2016",

month = oct,

day = "13",

doi = "10.1109/DASC-PICom-DataCom-CyberSciTec.2016.149",

language = "English",

isbn = "9781509040667",

pages = "874--877",

editor = "Randall Bilof",

booktitle = "Proceedings - 2016 IEEE Cyber Science and Technology Congress (CyberSciTech 2016), 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing (DASC 2016), 2016 IEEE 14th International Conference on Pervasive Intelligence and Com",

publisher = "IEEE",

}

Wei, J, He, J, Chen, K, Zhou, Y & Tang, Z 2016, Collaborative filtering and deep learning based hybrid recommendation for cold start problem. in R Bilof (ed.), Proceedings - 2016 IEEE Cyber Science and Technology Congress (CyberSciTech 2016), 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing (DASC 2016), 2016 IEEE 14th International Conference on Pervasive Intelligence and Com. IEEE, Piscataway, pp. 874-877. https://doi.org/10.1109/DASC-PICom-DataCom-CyberSciTec.2016.149

Collaborative filtering and deep learning based hybrid recommendation for cold start problem. / Wei, Jian; He, Jianhua; Chen, Kai (Lead / Corresponding author) et al.
Proceedings - 2016 IEEE Cyber Science and Technology Congress (CyberSciTech 2016), 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing (DASC 2016), 2016 IEEE 14th International Conference on Pervasive Intelligence and Com. ed. / Randall Bilof. Piscataway: IEEE, 2016. p. 874-877.

Research output: Chapter in Book/Report/Conference proceeding › Chapter

TY - CHAP

T1 - Collaborative filtering and deep learning based hybrid recommendation for cold start problem

AU - Wei, Jian

AU - He, Jianhua

AU - Chen, Kai

AU - Zhou, Yi

AU - Tang, Zuoyin

PY - 2016/10/13

Y1 - 2016/10/13

N2 - Recommender systems (RS) are used by many social networking applications and online e-commercial services. Collaborative filtering (CF) is one of the most popular approaches used for RS. However traditional CF approach suffers from sparsity and cold start problems. In this paper, we propose a hybrid recommendation model to address the cold start problem, which explores the item content features learned from a deep learning neural network and applies them to the timeSVD++ CF model. Extensive experiments are run on a large Netflix rating dataset for movies. Experiment results show that the proposed hybrid recommendation model provides a good prediction for cold start items, and performs better than four existing recommendation models for rating of non-cold start items.

AB - Recommender systems (RS) are used by many social networking applications and online e-commercial services. Collaborative filtering (CF) is one of the most popular approaches used for RS. However traditional CF approach suffers from sparsity and cold start problems. In this paper, we propose a hybrid recommendation model to address the cold start problem, which explores the item content features learned from a deep learning neural network and applies them to the timeSVD++ CF model. Extensive experiments are run on a large Netflix rating dataset for movies. Experiment results show that the proposed hybrid recommendation model provides a good prediction for cold start items, and performs better than four existing recommendation models for rating of non-cold start items.

KW - collaboration

KW - computational modeling

KW - data models

KW - machine learning

KW - motion pictures

KW - predictive models

KW - training

KW - Computer Vision and Pattern Recognition

KW - Information Systems

KW - Computer Science (miscellaneous)

KW - Artificial Intelligence

KW - Computer Networks and Communications

U2 - 10.1109/DASC-PICom-DataCom-CyberSciTec.2016.149

DO - 10.1109/DASC-PICom-DataCom-CyberSciTec.2016.149

M3 - Chapter

SN - 9781509040667

SP - 874

EP - 877

BT - Proceedings - 2016 IEEE Cyber Science and Technology Congress (CyberSciTech 2016), 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing (DASC 2016), 2016 IEEE 14th International Conference on Pervasive Intelligence and Com

A2 - Bilof, Randall

PB - IEEE

CY - Piscataway

ER -

Wei J, He J, Chen K, Zhou Y, Tang Z. Collaborative filtering and deep learning based hybrid recommendation for cold start problem. In Bilof R, editor, Proceedings - 2016 IEEE Cyber Science and Technology Congress (CyberSciTech 2016), 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing (DASC 2016), 2016 IEEE 14th International Conference on Pervasive Intelligence and Com. Piscataway: IEEE. 2016. p. 874-877 doi: 10.1109/DASC-PICom-DataCom-CyberSciTec.2016.149

Collaborative filtering and deep learning based hybrid recommendation for cold start problem

Abstract

Keywords

Access to Document

Fingerprint

Cite this