The Love-Hate Square Counting Method for Recommender Systems

Joseph S. Kong, Kyle Teague, Justin Kessler
Proceedings of KDD Cup 2011, PMLR 18:249-261, 2012.

Abstract

Recommender systems provide personalized suggestions to users and are critical to the success of many e-commerce sites, such as Netflix and Amazon. Outside of e-commerce, recommender systems can be deployed in fields such as intelligence analysis, for recommending high-quality information source to analysts for further examination. In this work, we present the square counting method for rating predictions in recommender systems. Our method is based on analyzing the bipartite rating network with score-labeled edges representing user nodes’ ratings to item nodes. Edges are denoted as an I-love-it or I-hate-it edge based on whether the rating score on the edge is above or below a threshold. For a target user-item pair, we count the number for each configuration of love-hate squares that involve the target pair, where the sequence of I-love-it or I-hate-it edges determine the particular configuration. The counts are used as features in a supervised machine learning framework for training and rating prediction. The method is implemented and empirically evaluated on a large-scale Yahoo! music user-item rating dataset. Results show that the square counting method is fast, simple to parallelize, scalable to massive datasets and makes highly accurate predictions. Finally, we report an interesting empirical finding that configurations with consecutive I-hate-it edges seem to provide the most powerful signal in predicting a user’s love for an item.

Cite this Paper


BibTeX
@InProceedings{pmlr-v18-kong12a, title = {The Love-Hate Square Counting Method for Recommender Systems}, author = {Kong, Joseph S. and Teague, Kyle and Kessler, Justin}, booktitle = {Proceedings of KDD Cup 2011}, pages = {249--261}, 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/kong12a/kong12a.pdf}, url = {https://proceedings.mlr.press/v18/kong12a.html}, abstract = {Recommender systems provide personalized suggestions to users and are critical to the success of many e-commerce sites, such as Netflix and Amazon. Outside of e-commerce, recommender systems can be deployed in fields such as intelligence analysis, for recommending high-quality information source to analysts for further examination. In this work, we present the square counting method for rating predictions in recommender systems. Our method is based on analyzing the bipartite rating network with score-labeled edges representing user nodes’ ratings to item nodes. Edges are denoted as an I-love-it or I-hate-it edge based on whether the rating score on the edge is above or below a threshold. For a target user-item pair, we count the number for each configuration of love-hate squares that involve the target pair, where the sequence of I-love-it or I-hate-it edges determine the particular configuration. The counts are used as features in a supervised machine learning framework for training and rating prediction. The method is implemented and empirically evaluated on a large-scale Yahoo! music user-item rating dataset. Results show that the square counting method is fast, simple to parallelize, scalable to massive datasets and makes highly accurate predictions. Finally, we report an interesting empirical finding that configurations with consecutive I-hate-it edges seem to provide the most powerful signal in predicting a user’s love for an item.} }
Endnote
%0 Conference Paper %T The Love-Hate Square Counting Method for Recommender Systems %A Joseph S. Kong %A Kyle Teague %A Justin Kessler %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-kong12a %I PMLR %P 249--261 %U https://proceedings.mlr.press/v18/kong12a.html %V 18 %X Recommender systems provide personalized suggestions to users and are critical to the success of many e-commerce sites, such as Netflix and Amazon. Outside of e-commerce, recommender systems can be deployed in fields such as intelligence analysis, for recommending high-quality information source to analysts for further examination. In this work, we present the square counting method for rating predictions in recommender systems. Our method is based on analyzing the bipartite rating network with score-labeled edges representing user nodes’ ratings to item nodes. Edges are denoted as an I-love-it or I-hate-it edge based on whether the rating score on the edge is above or below a threshold. For a target user-item pair, we count the number for each configuration of love-hate squares that involve the target pair, where the sequence of I-love-it or I-hate-it edges determine the particular configuration. The counts are used as features in a supervised machine learning framework for training and rating prediction. The method is implemented and empirically evaluated on a large-scale Yahoo! music user-item rating dataset. Results show that the square counting method is fast, simple to parallelize, scalable to massive datasets and makes highly accurate predictions. Finally, we report an interesting empirical finding that configurations with consecutive I-hate-it edges seem to provide the most powerful signal in predicting a user’s love for an item.
RIS
TY - CPAPER TI - The Love-Hate Square Counting Method for Recommender Systems AU - Joseph S. Kong AU - Kyle Teague AU - Justin Kessler BT - Proceedings of KDD Cup 2011 DA - 2012/06/01 ED - Gideon Dror ED - Yehuda Koren ED - Markus Weimer ID - pmlr-v18-kong12a PB - PMLR DP - Proceedings of Machine Learning Research VL - 18 SP - 249 EP - 261 L1 - http://proceedings.mlr.press/v18/kong12a/kong12a.pdf UR - https://proceedings.mlr.press/v18/kong12a.html AB - Recommender systems provide personalized suggestions to users and are critical to the success of many e-commerce sites, such as Netflix and Amazon. Outside of e-commerce, recommender systems can be deployed in fields such as intelligence analysis, for recommending high-quality information source to analysts for further examination. In this work, we present the square counting method for rating predictions in recommender systems. Our method is based on analyzing the bipartite rating network with score-labeled edges representing user nodes’ ratings to item nodes. Edges are denoted as an I-love-it or I-hate-it edge based on whether the rating score on the edge is above or below a threshold. For a target user-item pair, we count the number for each configuration of love-hate squares that involve the target pair, where the sequence of I-love-it or I-hate-it edges determine the particular configuration. The counts are used as features in a supervised machine learning framework for training and rating prediction. The method is implemented and empirically evaluated on a large-scale Yahoo! music user-item rating dataset. Results show that the square counting method is fast, simple to parallelize, scalable to massive datasets and makes highly accurate predictions. Finally, we report an interesting empirical finding that configurations with consecutive I-hate-it edges seem to provide the most powerful signal in predicting a user’s love for an item. ER -
APA
Kong, J.S., Teague, K. & Kessler, J.. (2012). The Love-Hate Square Counting Method for Recommender Systems. Proceedings of KDD Cup 2011, in Proceedings of Machine Learning Research 18:249-261 Available from https://proceedings.mlr.press/v18/kong12a.html.

Related Material