%0 Journal Article %1 busafekete2012appletoapple %A Busa-Fekete, R. %A Szarvas, Gy. %A Éltető, T. %A Kégl, B. %B B. Proceedings of ECAI-12 Workshop, Preference Learning: Problems and Applications in AI %D 2012 %K comparison comulative discounted gain learning ranking %T An apple-to-apple comparison of Learning-to-rank algorithms in terms of Normalized Discounted Cumulative Gain %U http://www.inf.u-szeged.hu/~busarobi/publ.html %X 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

@article{busafekete2012appletoapple, 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}, added-at = {2013-01-13T13:19:29.000+0100}, author = {Busa-Fekete, R. and Szarvas, Gy. and Éltető, T. and Kégl, B.}, biburl = {https://www.bibsonomy.org/bibtex/209ff03936653f0e846b214bab2f5256d/nosebrain}, booktitle = {B. Proceedings of ECAI-12 Workshop, Preference Learning: Problems and Applications in AI}, interhash = {0bd6c0e50f7205d44b5962d792462ccb}, intrahash = {09ff03936653f0e846b214bab2f5256d}, keywords = {comparison comulative discounted gain learning ranking}, timestamp = {2013-01-13T13:19:29.000+0100}, title = {An apple-to-apple comparison of Learning-to-rank algorithms in terms of Normalized Discounted Cumulative Gain}, url = {http://www.inf.u-szeged.hu/~busarobi/publ.html}, year = 2012 }