Impact of data characteristics on recommender systems performance

Gediminas Adomavicius, Jingjing Zhang

Research output: Contribution to journalArticlepeer-review

51 Scopus citations

Abstract

This article investigates the impact of rating data characteristics on the performance of several popular recommendation algorithms, including user-based and item-based collaborative filtering, as well as matrix factorization. We focus on three groups of data characteristics: rating space, rating frequency distribution, and rating value distribution. A sampling procedure was employed to obtain different rating data subsamples with varying characteristics; recommendation algorithms were used to estimate the predictive accuracy for each sample; and linear regression-based models were used to uncover the relationships between data characteristics and recommendation accuracy. Experimental results on multiple rating datasets show the consistent and significant effects of several data characteristics on recommendation accuracy.

Original languageEnglish (US)
Article number3
JournalACM Transactions on Management Information Systems
Volume3
Issue number1
DOIs
StatePublished - Apr 2012

Keywords

  • Accuracy of recommendation algorithms
  • Algorithms
  • Collaborative filtering
  • Data characteristics
  • Experimentation
  • Performance
  • Performance of recommender systems

Fingerprint

Dive into the research topics of 'Impact of data characteristics on recommender systems performance'. Together they form a unique fingerprint.

Cite this