Abstract
In real-world scenarios, recommenders face non-functional requirementsof technical nature and must handle dynamic data in the formof sequential streams. Evaluation of recommender systems musttake these issues into account in order to be maximally informative.In this paper, we present Idomaar—a framework that enables theefficient multi-dimensional benchmarking of recommender algorithms.Idomaar goes beyond current academic research practicesby creating a realistic evaluation environment and computing botheffectiveness and technical metrics for stream-based as well as setbasedevaluation. A scenario focussing on “research to prototypingto productization” cycle at a company illustrates Idomaar’s potential.We show that Idomaar simplifies testing with varying configurationsand supports flexible integration of different data.
Original language | English |
---|---|
Title of host publication | Poster Proceedings of ACM RecSys 2016 |
Subtitle of host publication | Proceedings of the Poster Track of the 10th ACM Conference on Recommender Systems, RecSys 2016 |
Editors | Ido Guy, Amit Sharma |
Place of Publication | Aachen |
Publisher | CEUR-WS |
Pages | 1-2 |
Number of pages | 2 |
Publication status | Published - Sept 2016 |
Event | 10th ACM Conference on Recommender Systems, RecSys 2016 - MIT, Boston, MA, United States Duration: 15 Sept 2016 → 19 Sept 2016 https://recsys.acm.org/recsys16/ |
Publication series
Name | CEUR Workshop Proceedings |
---|---|
Volume | 1688 |
ISSN (Print) | 1613-0073 |
Conference
Conference | 10th ACM Conference on Recommender Systems, RecSys 2016 |
---|---|
Country/Territory | United States |
City | Boston, MA |
Period | 15/09/16 → 19/09/16 |
Internet address |