PUMA publications for /author/Gediminas%20Adomavicius/characteristicshttps://puma.uni-kassel.de/author/Gediminas%20Adomavicius/characteristicsPUMA RSS feed for /author/Gediminas%20Adomavicius/characteristics2024-03-28T19:59:07+01:00Impact of Data Characteristics on Recommender Systems Performancehttps://puma.uni-kassel.de/bibtex/2e41453a56391ca382f2298607b361208/stephandoerfelstephandoerfel2014-08-06T18:12:26+02:00characteristics dataset model recommender dependence evaluation <span class="authorEditorList"><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Gediminas Adomavicius" itemprop="url" href="/author/Gediminas%20Adomavicius"><span itemprop="name">G. Adomavicius</span></a></span>, und <span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Jingjing Zhang" itemprop="url" href="/author/Jingjing%20Zhang"><span itemprop="name">J. Zhang</span></a></span>. </span><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><span itemtype="http://schema.org/Periodical" itemscope="itemscope" itemprop="isPartOf"><span itemprop="name"><em>ACM Trans. Manage. Inf. Syst.</em></span></span> <em><span itemtype="http://schema.org/PublicationVolume" itemscope="itemscope" itemprop="isPartOf"><span itemprop="volumeNumber">3 </span></span>(<span itemprop="issueNumber">1</span>):
<span itemprop="pagination">3:1--3:17</span></em> </span>(<em><span>April 2012<meta content="April 2012" itemprop="datePublished"/></span></em>)Wed Aug 06 18:12:26 CEST 2014New York, NY, USAACM Trans. Manage. Inf. Syst.apr13:1--3:17Impact of Data Characteristics on Recommender Systems Performance32012characteristics dataset model recommender dependence evaluation 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.Impact of data characteristics on recommender systems performance