Skip to Main content Skip to Navigation
Conference papers

An apple-to-apple comparison of Learning-to-rank algorithms in terms of Normalized Discounted Cumulative Gain

Abstract : The Normalized Discounted Cumulative Gain (NDCG) is a widely used evaluation metric for learning-to-rank (LTR) systems. NDCG is designed for ranking tasks with more than one relevance levels. There are many freely available, open source tools for computing the NDCG score for a ranked result list. Even though the definition of NDCG is unambiguous, the various tools can produce different scores for ranked lists with certain properties, deteriorating the empirical tests in many published papers and thereby making the comparison of empirical results published in different studies difficult to compare. In this study, first, we identify the major differences between the various publicly available NDCG evaluation tools. Second, based on a set of comparative experiments using a common benchmark dataset in LTR research and 6 different LTR algorithms, we demonstrate how these differences affect the overall performance of different algorithms and the final scores that are used to compare different systems.
Document type :
Conference papers
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

http://hal.in2p3.fr/in2p3-00726760
Contributor : Sabine Starita <>
Submitted on : Friday, August 31, 2012 - 11:27:55 AM
Last modification on : Wednesday, September 16, 2020 - 5:13:10 PM
Long-term archiving on: : Saturday, December 1, 2012 - 3:30:57 AM

File

07-busa-fekete.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : in2p3-00726760, version 1

Collections

Citation

Róbert Busa-Fekete, György Szarvas, Tamás Élteto, B. Kégl. An apple-to-apple comparison of Learning-to-rank algorithms in terms of Normalized Discounted Cumulative Gain. ECAI 2012 - 20th European Conference on Artificial Intelligence : Preference Learning: Problems and Applications in AI Workshop, Aug 2012, Montpellier, France. ⟨in2p3-00726760⟩

Share

Metrics

Record views

1234

Files downloads

1877