Hybrid Recommendation Models for Binary User Preference Prediction Problem

Siwei Lai, Yang Liu, Huxiang Gu, Liheng Xu, Kang Liu, Shiming Xiang, Jun Zhao, Rui Diao, Liang Xiang, Hang Li, Dong Wang
Proceedings of KDD Cup 2011, PMLR 18:137-151, 2012.

Abstract

This paper presents detailed information of our solutions to the task 2 of KDD Cup 2011. The task 2 is called binary user preference prediction problem in the paper because it aims at separating tracks rated highly by specific users from tracks not rated by them, and the solutions of this task can be easily applied to binary user behavior data. In the contest, we firstly implemented many different models, including neighborhood-based models, latent factor models, content-based models, etc. Then, linear combination is used to combine different models together. Finally, we used robust post-processing to further refine the special user-item pairs. The final error rate is 2.4808% which placed number 2 in the Leaderboard.

Cite this Paper

BibTeX
@InProceedings{pmlr-v18-lai12a, title = {Hybrid Recommendation Models for Binary User Preference Prediction Problem}, author = {Lai, Siwei and Liu, Yang and Gu, Huxiang and Xu, Liheng and Liu, Kang and Xiang, Shiming and Zhao, Jun and Diao, Rui and Xiang, Liang and Li, Hang and Wang, Dong}, booktitle = {Proceedings of KDD Cup 2011}, pages = {137--151}, year = {2012}, editor = {Dror, Gideon and Koren, Yehuda and Weimer, Markus}, volume = {18}, series = {Proceedings of Machine Learning Research}, month = {21 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v18/lai12a/lai12a.pdf}, url = {https://proceedings.mlr.press/v18/lai12a.html}, abstract = {This paper presents detailed information of our solutions to the task 2 of KDD Cup 2011. The task 2 is called binary user preference prediction problem in the paper because it aims at separating tracks rated highly by specific users from tracks not rated by them, and the solutions of this task can be easily applied to binary user behavior data. In the contest, we firstly implemented many different models, including neighborhood-based models, latent factor models, content-based models, etc. Then, linear combination is used to combine different models together. Finally, we used robust post-processing to further refine the special user-item pairs. The final error rate is 2.4808% which placed number 2 in the Leaderboard.} }
Endnote
%0 Conference Paper %T Hybrid Recommendation Models for Binary User Preference Prediction Problem %A Siwei Lai %A Yang Liu %A Huxiang Gu %A Liheng Xu %A Kang Liu %A Shiming Xiang %A Jun Zhao %A Rui Diao %A Liang Xiang %A Hang Li %A Dong Wang %B Proceedings of KDD Cup 2011 %C Proceedings of Machine Learning Research %D 2012 %E Gideon Dror %E Yehuda Koren %E Markus Weimer %F pmlr-v18-lai12a %I PMLR %P 137--151 %U https://proceedings.mlr.press/v18/lai12a.html %V 18 %X This paper presents detailed information of our solutions to the task 2 of KDD Cup 2011. The task 2 is called binary user preference prediction problem in the paper because it aims at separating tracks rated highly by specific users from tracks not rated by them, and the solutions of this task can be easily applied to binary user behavior data. In the contest, we firstly implemented many different models, including neighborhood-based models, latent factor models, content-based models, etc. Then, linear combination is used to combine different models together. Finally, we used robust post-processing to further refine the special user-item pairs. The final error rate is 2.4808% which placed number 2 in the Leaderboard.
RIS
TY - CPAPER TI - Hybrid Recommendation Models for Binary User Preference Prediction Problem AU - Siwei Lai AU - Yang Liu AU - Huxiang Gu AU - Liheng Xu AU - Kang Liu AU - Shiming Xiang AU - Jun Zhao AU - Rui Diao AU - Liang Xiang AU - Hang Li AU - Dong Wang BT - Proceedings of KDD Cup 2011 DA - 2012/06/01 ED - Gideon Dror ED - Yehuda Koren ED - Markus Weimer ID - pmlr-v18-lai12a PB - PMLR DP - Proceedings of Machine Learning Research VL - 18 SP - 137 EP - 151 L1 - http://proceedings.mlr.press/v18/lai12a/lai12a.pdf UR - https://proceedings.mlr.press/v18/lai12a.html AB - This paper presents detailed information of our solutions to the task 2 of KDD Cup 2011. The task 2 is called binary user preference prediction problem in the paper because it aims at separating tracks rated highly by specific users from tracks not rated by them, and the solutions of this task can be easily applied to binary user behavior data. In the contest, we firstly implemented many different models, including neighborhood-based models, latent factor models, content-based models, etc. Then, linear combination is used to combine different models together. Finally, we used robust post-processing to further refine the special user-item pairs. The final error rate is 2.4808% which placed number 2 in the Leaderboard. ER -
APA
Lai, S., Liu, Y., Gu, H., Xu, L., Liu, K., Xiang, S., Zhao, J., Diao, R., Xiang, L., Li, H. & Wang, D.. (2012). Hybrid Recommendation Models for Binary User Preference Prediction Problem. Proceedings of KDD Cup 2011, in Proceedings of Machine Learning Research 18:137-151 Available from https://proceedings.mlr.press/v18/lai12a.html.

Related Material