Welcome to the InfoSci Platform
Reference Hub5
A Systematic Study of Feature Selection Methods for Learning to Rank Algorithms

A Systematic Study of Feature Selection Methods for Learning to Rank Algorithms

Mehrnoush Barani Shirzad, Mohammad Reza Keyvanpour
Copyright: © 2018 |Volume: 8 |Issue: 3 |Pages: 22
ISSN: 2155-6377|EISSN: 2155-6385|EISBN13: 9781522545651|DOI: 10.4018/IJIRR.2018070104
Cite Article Cite Article

MLA

Shirzad, Mehrnoush Barani, and Mohammad Reza Keyvanpour. "A Systematic Study of Feature Selection Methods for Learning to Rank Algorithms." IJIRR vol.8, no.3 2018: pp.46-67. http://doi.org/10.4018/IJIRR.2018070104

APA

Shirzad, M. B. & Keyvanpour, M. R. (2018). A Systematic Study of Feature Selection Methods for Learning to Rank Algorithms. International Journal of Information Retrieval Research (IJIRR), 8(3), 46-67. http://doi.org/10.4018/IJIRR.2018070104

Chicago

Shirzad, Mehrnoush Barani, and Mohammad Reza Keyvanpour. "A Systematic Study of Feature Selection Methods for Learning to Rank Algorithms," International Journal of Information Retrieval Research (IJIRR) 8, no.3: 46-67. http://doi.org/10.4018/IJIRR.2018070104

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

This article describes how feature selection for learning to rank algorithms has become an interesting issue. While noisy and irrelevant features influence performance, and result in an overfitting problem in ranking systems, reducing the number of features by illuminating irrelevant and noisy features is a solution. Several studies have applied feature selection for learning to rank, which promote efficiency and effectiveness of ranking models. As the number of features and consequently the number of irrelevant and noisy features is increasing, systematic a review of Feature selection for learning to rank methods is required. In this article, a framework to examine research on feature selection for learning to rank (FSLR) is proposed. Under this framework, the authors review the most state-of-the-art methods and suggest several criteria to analyze them. FSLR offers a structured classification of current algorithms for future research to: a) properly select strategies from existing algorithms using certain criteria or b) to find ways to develop existing methodologies.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.