Graduate Project
 

A collaborative filtering algorithm and evaluation metric that accurately model the user experience

Pubblico Deposited

Contenuto scaricabile

Scarica il pdf
https://ir.library.oregonstate.edu/concern/graduate_projects/g732d909z

Descriptions

Attribute NameValues
Creator
Abstract
  • "Collaborative filtering algorithms’ performances have been evaluated using a variety of metrics. These metrics, such as Mean Absolute Error and Precision, have often ignored recommendations for which they do not have data. Ignoring these recommendations has provided numbers which do not accurately represent the user experience. Qualitatively we have seen that User-User and Item-Item algorithms are often plagued with obscure recommendations. This flaw was illustrated quantitatively by the extremely low modified Precision scores. To address this problem and provide a better user experience we proposed a new Belief Distribution Algorithm. Our Belief Distribution Algorithm retained comparable predictive capabilities to previous nearest-neighbor algorithms while achieving far superior results for recommendations. In the future, we plan to run a user study in which a complete set of ratings is collected, enabling us to evaluate just how accurately modified precision measures the user experience and look for significant gaps where it does not."--Conclusion and future work.
Resource Type
Date Available
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Subject
Dichiarazione dei diritti
Publisher
Peer Reviewed
Language
Replaces

Le relazioni

Parents:

This work has no parents.

Elementi

Thumbnail Titolo Data caricata Visibilità Azioni
file details 2005-78.pdf 2017-07-05 Pubblico Scaricare