Committee Based Prediction System for Recommendation: KDD Cup 2011, Track2

Hang Zhang, Eric Riedl, Valery Petrushin, Siddharth Pal, Jacob Spoelstra
Proceedings of KDD Cup 2011, PMLR 18:215-229, 2012.

Abstract

This paper describes a solution to the 2011 KDD Cup competition, Track2: discriminating between highly rated tracks and unrated tracks in a Yahoo! Music dataset. Our approach was to use supervised learning based on 65 features generated using various techniques such as collaborative filtering, SVD, and similarity scoring. During our modeling stage, we created a number of predictors including logistic regression, artificial neural networks and gradient-boosted decision trees. To further improve robustness and reduce the variance, we used three of our top performing models and took a weighted average for the final submission, which achieved 4.3768% error.

Cite this Paper

BibTeX
@InProceedings{pmlr-v18-zhang12a, title = {Committee Based Prediction System for Recommendation: {KDD} Cup 2011, Track2}, author = {Zhang, Hang and Riedl, Eric and Petrushin, Valery and Pal, Siddharth and Spoelstra, Jacob}, booktitle = {Proceedings of KDD Cup 2011}, pages = {215--229}, 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/zhang12a/zhang12a.pdf}, url = {https://proceedings.mlr.press/v18/zhang12a.html}, abstract = {This paper describes a solution to the 2011 KDD Cup competition, Track2: discriminating between highly rated tracks and unrated tracks in a Yahoo! Music dataset. Our approach was to use supervised learning based on 65 features generated using various techniques such as collaborative filtering, SVD, and similarity scoring. During our modeling stage, we created a number of predictors including logistic regression, artificial neural networks and gradient-boosted decision trees. To further improve robustness and reduce the variance, we used three of our top performing models and took a weighted average for the final submission, which achieved 4.3768% error.} }
Endnote
%0 Conference Paper %T Committee Based Prediction System for Recommendation: KDD Cup 2011, Track2 %A Hang Zhang %A Eric Riedl %A Valery Petrushin %A Siddharth Pal %A Jacob Spoelstra %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-zhang12a %I PMLR %P 215--229 %U https://proceedings.mlr.press/v18/zhang12a.html %V 18 %X This paper describes a solution to the 2011 KDD Cup competition, Track2: discriminating between highly rated tracks and unrated tracks in a Yahoo! Music dataset. Our approach was to use supervised learning based on 65 features generated using various techniques such as collaborative filtering, SVD, and similarity scoring. During our modeling stage, we created a number of predictors including logistic regression, artificial neural networks and gradient-boosted decision trees. To further improve robustness and reduce the variance, we used three of our top performing models and took a weighted average for the final submission, which achieved 4.3768% error.
RIS
TY - CPAPER TI - Committee Based Prediction System for Recommendation: KDD Cup 2011, Track2 AU - Hang Zhang AU - Eric Riedl AU - Valery Petrushin AU - Siddharth Pal AU - Jacob Spoelstra BT - Proceedings of KDD Cup 2011 DA - 2012/06/01 ED - Gideon Dror ED - Yehuda Koren ED - Markus Weimer ID - pmlr-v18-zhang12a PB - PMLR DP - Proceedings of Machine Learning Research VL - 18 SP - 215 EP - 229 L1 - http://proceedings.mlr.press/v18/zhang12a/zhang12a.pdf UR - https://proceedings.mlr.press/v18/zhang12a.html AB - This paper describes a solution to the 2011 KDD Cup competition, Track2: discriminating between highly rated tracks and unrated tracks in a Yahoo! Music dataset. Our approach was to use supervised learning based on 65 features generated using various techniques such as collaborative filtering, SVD, and similarity scoring. During our modeling stage, we created a number of predictors including logistic regression, artificial neural networks and gradient-boosted decision trees. To further improve robustness and reduce the variance, we used three of our top performing models and took a weighted average for the final submission, which achieved 4.3768% error. ER -
APA
Zhang, H., Riedl, E., Petrushin, V., Pal, S. & Spoelstra, J.. (2012). Committee Based Prediction System for Recommendation: KDD Cup 2011, Track2. Proceedings of KDD Cup 2011, in Proceedings of Machine Learning Research 18:215-229 Available from https://proceedings.mlr.press/v18/zhang12a.html.

Related Material