Ensemble methods for improving the performance of neighborhood-based collaborative filtering

Alon Schclar, Alexander Tsikinovsky, Lior Rokach, Amnon Meisels, Liat Antwarg

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

31 Scopus citations

Abstract

Recommender systems provide consumers with ratings of items. These ratings are based on a set of ratings that were obtained from a wide scope of users. Predicting the ratings can be formulated as a regression problem. Ensemble regression methods are effective tools that improve the results of simple regression algorithms by iteratively applying the simple algorithm to a diverse set of inputs. The present paper describes a simple and effective ensemble regressor for the prediction of missing ratings in recommender systems. The ensemble method is an adaptation of the AdaBoost regression algorithm for recommendation tasks. In all iterations, interpolation weights for all nearest neighbors are simultaneously derived by minimizing the root mean squared error. From iteration to iteration instances that are hard to predict are reinforced by manipulating their weights in the goal function that needs to be minimized. The experimental evaluation demonstrates that the ensemble methodology significantly improves the predictive performance of single neighborhood-based collaborative filtering.

Original languageEnglish
Title of host publicationRecSys'09 - Proceedings of the 3rd ACM Conference on Recommender Systems
Pages261-264
Number of pages4
DOIs
StatePublished - 2009
Externally publishedYes
Event3rd ACM Conference on Recommender Systems, RecSys'09 - New York, NY, United States
Duration: 23 Oct 200925 Oct 2009

Publication series

NameRecSys'09 - Proceedings of the 3rd ACM Conference on Recommender Systems

Conference

Conference3rd ACM Conference on Recommender Systems, RecSys'09
Country/TerritoryUnited States
CityNew York, NY
Period23/10/0925/10/09

Keywords

  • Collaborative filtering
  • Ensemble methods
  • Neighborhood based collaborative filtering

Fingerprint

Dive into the research topics of 'Ensemble methods for improving the performance of neighborhood-based collaborative filtering'. Together they form a unique fingerprint.

Cite this