Advanced search
1 file | 811.50 KB Add to list

Integrating expert and novice evaluations for augmenting ordinal regression models

Marc Sader (UGent) , Jan Verwaeren (UGent) , Raul Perez Fernandez (UGent) and Bernard De Baets (UGent)
(2019) INFORMATION FUSION. 51. p.1-9
Author
Organization
Abstract
We consider a predictive modelling problem, where the goal is to predict the absolute evaluation of an object on an ordinal scale, traditionally known as an ordinal regression problem. We present a framework that is capable of learning such a model while combining different types of information: absolute evaluations by experts and relative evaluations by novices. We propose and solve a linearly constrained convex optimization problem that takes both types of information into account, and is capable of attributing an ordinal label to a new object based on its features. We do this by relying on principles from machine learning and optimization theory, combined with ideas from information fusion. Experimental results demonstrate the enhanced performance of ordinal regression models when incorporating relative evaluations in the form of rankings.
Keywords
Preference integration, Ordinal regression, Constrained optimization, SPECTROSCOPY DATA, RANKING, SCALE, SOFTWARE

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 811.50 KB

Citation

Please use this url to cite or link to this publication:

MLA
Sader, Marc et al. “Integrating Expert and Novice Evaluations for Augmenting Ordinal Regression Models.” INFORMATION FUSION 51 (2019): 1–9. Print.
APA
Sader, M., Verwaeren, J., Perez Fernandez, R., & De Baets, B. (2019). Integrating expert and novice evaluations for augmenting ordinal regression models. INFORMATION FUSION, 51, 1–9.
Chicago author-date
Sader, Marc, Jan Verwaeren, Raul Perez Fernandez, and Bernard De Baets. 2019. “Integrating Expert and Novice Evaluations for Augmenting Ordinal Regression Models.” Information Fusion 51: 1–9.
Chicago author-date (all authors)
Sader, Marc, Jan Verwaeren, Raul Perez Fernandez, and Bernard De Baets. 2019. “Integrating Expert and Novice Evaluations for Augmenting Ordinal Regression Models.” Information Fusion 51: 1–9.
Vancouver
1.
Sader M, Verwaeren J, Perez Fernandez R, De Baets B. Integrating expert and novice evaluations for augmenting ordinal regression models. INFORMATION FUSION. 2019;51:1–9.
IEEE
[1]
M. Sader, J. Verwaeren, R. Perez Fernandez, and B. De Baets, “Integrating expert and novice evaluations for augmenting ordinal regression models,” INFORMATION FUSION, vol. 51, pp. 1–9, 2019.
@article{8607565,
  abstract     = {We consider a predictive modelling problem, where the goal is to predict the absolute evaluation of an object on an ordinal scale, traditionally known as an ordinal regression problem. We present a framework that is capable of learning such a model while combining different types of information: absolute evaluations by experts and relative evaluations by novices. We propose and solve a linearly constrained convex optimization problem that takes both types of information into account, and is capable of attributing an ordinal label to a new object based on its features. We do this by relying on principles from machine learning and optimization theory, combined with ideas from information fusion. Experimental results demonstrate the enhanced performance of ordinal regression models when incorporating relative evaluations in the form of rankings.},
  author       = {Sader, Marc and Verwaeren, Jan and Perez Fernandez, Raul and De Baets, Bernard},
  issn         = {1566-2535},
  journal      = {INFORMATION FUSION},
  keywords     = {Preference integration,Ordinal regression,Constrained optimization,SPECTROSCOPY DATA,RANKING,SCALE,SOFTWARE},
  language     = {eng},
  pages        = {1--9},
  title        = {Integrating expert and novice evaluations for augmenting ordinal regression models},
  url          = {http://dx.doi.org/10.1016/j.inffus.2018.10.012},
  volume       = {51},
  year         = {2019},
}

Altmetric
View in Altmetric
Web of Science
Times cited: