Average Gain Ratio

A Simple Retrieval Performance Measure for Evaluation with Multiple Relevance Levels

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Average gain ratio which is based on the idea of cumulative gain and is used for evaluation with multiple relevance levels, is proposed. Cumulative gain assumes that an imaginary user scans the ranked output from the top, and 'gains' an additional score each time he finds a relevant document. Average gain ratio was proposed as a modification of weighted average precision. The results show that average gain ratio is more suitable for averaging across topics and is more robust to the variation in the number of relevant documents at each relevance level.

Original languageEnglish
Pages (from-to)417-418
Number of pages2
JournalSIGIR Forum (ACM Special Interest Group on Information Retrieval)
Issue numberSPEC. ISS.
Publication statusPublished - 2003
Externally publishedYes

Fingerprint

Evaluation
Performance measures

Keywords

  • Average Gain Ratio
  • Retrieval Performance

ASJC Scopus subject areas

  • Hardware and Architecture
  • Management Information Systems

Cite this

@article{ef4dbcf73c2d49f5b48b92e08d56eeb8,
title = "Average Gain Ratio: A Simple Retrieval Performance Measure for Evaluation with Multiple Relevance Levels",
abstract = "Average gain ratio which is based on the idea of cumulative gain and is used for evaluation with multiple relevance levels, is proposed. Cumulative gain assumes that an imaginary user scans the ranked output from the top, and 'gains' an additional score each time he finds a relevant document. Average gain ratio was proposed as a modification of weighted average precision. The results show that average gain ratio is more suitable for averaging across topics and is more robust to the variation in the number of relevant documents at each relevance level.",
keywords = "Average Gain Ratio, Retrieval Performance",
author = "Tetsuya Sakai",
year = "2003",
language = "English",
pages = "417--418",
journal = "SIGIR Forum (ACM Special Interest Group on Information Retrieval)",
issn = "0163-5840",
publisher = "Association for Computing Machinery (ACM)",
number = "SPEC. ISS.",

}

TY - JOUR

T1 - Average Gain Ratio

T2 - A Simple Retrieval Performance Measure for Evaluation with Multiple Relevance Levels

AU - Sakai, Tetsuya

PY - 2003

Y1 - 2003

N2 - Average gain ratio which is based on the idea of cumulative gain and is used for evaluation with multiple relevance levels, is proposed. Cumulative gain assumes that an imaginary user scans the ranked output from the top, and 'gains' an additional score each time he finds a relevant document. Average gain ratio was proposed as a modification of weighted average precision. The results show that average gain ratio is more suitable for averaging across topics and is more robust to the variation in the number of relevant documents at each relevance level.

AB - Average gain ratio which is based on the idea of cumulative gain and is used for evaluation with multiple relevance levels, is proposed. Cumulative gain assumes that an imaginary user scans the ranked output from the top, and 'gains' an additional score each time he finds a relevant document. Average gain ratio was proposed as a modification of weighted average precision. The results show that average gain ratio is more suitable for averaging across topics and is more robust to the variation in the number of relevant documents at each relevance level.

KW - Average Gain Ratio

KW - Retrieval Performance

UR - http://www.scopus.com/inward/record.url?scp=1542377483&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1542377483&partnerID=8YFLogxK

M3 - Article

SP - 417

EP - 418

JO - SIGIR Forum (ACM Special Interest Group on Information Retrieval)

JF - SIGIR Forum (ACM Special Interest Group on Information Retrieval)

SN - 0163-5840

IS - SPEC. ISS.

ER -