The classifier chain generalized maximum entropy model for multi-label choice problems

© Springer International Publishing Switzerland 2015. Multi-label classification can be applied to study empirically discrete choice problems, in which each individual chooses more than one alternative. We applied the Classifier Chain (CC) method to transform the Generalized Maximum Entropy (GME) ch...

Full description

Saved in:
Bibliographic Details
Main Authors: Leurcharusmee S., Sirisrisakulchai J., Sriboonchitta S., Denoeux T.
Format: Article
Published: Springer Verlag 2015
Subjects:
Online Access:http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=84919344189&origin=inward
http://cmuir.cmu.ac.th/handle/6653943832/39142
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Chiang Mai University
id th-cmuir.6653943832-39142
record_format dspace
spelling th-cmuir.6653943832-391422015-06-16T08:07:44Z The classifier chain generalized maximum entropy model for multi-label choice problems Leurcharusmee S. Sirisrisakulchai J. Sriboonchitta S. Denoeux T. Artificial Intelligence © Springer International Publishing Switzerland 2015. Multi-label classification can be applied to study empirically discrete choice problems, in which each individual chooses more than one alternative. We applied the Classifier Chain (CC) method to transform the Generalized Maximum Entropy (GME) choice model from a single-label model to amulti-label model. The contribution of our CC-GME model lies in the advantages of both the GME and CC models. Specifically, the GME model can not only predict each individual’s choice, but also robustly estimate model parameters that describe factors determining his or her choices. The CC model is a problem transformationmethod that allows the decision on each alternative to be correlated. We used Monte-Carlo simulations and occupational hazard data to compare the CC-GME model with other selected methodologies for multi-label problems using the Hamming Loss, Accuracy, Precision and Recall measures. The results confirm the robustness of GME estimates with respect to relevant parameters regardless of the true error distributions. Moreover, the CC method outperforms other methods, indicating that the incorporation of the information on dependence patterns among alternatives can improve prediction performance. 2015-06-16T08:07:44Z 2015-06-16T08:07:44Z 2015-01-01 Article 1860949X 2-s2.0-84919344189 10.1007/978-3-319-13449-9_13 http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=84919344189&origin=inward http://cmuir.cmu.ac.th/handle/6653943832/39142 Springer Verlag
institution Chiang Mai University
building Chiang Mai University Library
country Thailand
collection CMU Intellectual Repository
topic Artificial Intelligence
spellingShingle Artificial Intelligence
Leurcharusmee S.
Sirisrisakulchai J.
Sriboonchitta S.
Denoeux T.
The classifier chain generalized maximum entropy model for multi-label choice problems
description © Springer International Publishing Switzerland 2015. Multi-label classification can be applied to study empirically discrete choice problems, in which each individual chooses more than one alternative. We applied the Classifier Chain (CC) method to transform the Generalized Maximum Entropy (GME) choice model from a single-label model to amulti-label model. The contribution of our CC-GME model lies in the advantages of both the GME and CC models. Specifically, the GME model can not only predict each individual’s choice, but also robustly estimate model parameters that describe factors determining his or her choices. The CC model is a problem transformationmethod that allows the decision on each alternative to be correlated. We used Monte-Carlo simulations and occupational hazard data to compare the CC-GME model with other selected methodologies for multi-label problems using the Hamming Loss, Accuracy, Precision and Recall measures. The results confirm the robustness of GME estimates with respect to relevant parameters regardless of the true error distributions. Moreover, the CC method outperforms other methods, indicating that the incorporation of the information on dependence patterns among alternatives can improve prediction performance.
format Article
author Leurcharusmee S.
Sirisrisakulchai J.
Sriboonchitta S.
Denoeux T.
author_facet Leurcharusmee S.
Sirisrisakulchai J.
Sriboonchitta S.
Denoeux T.
author_sort Leurcharusmee S.
title The classifier chain generalized maximum entropy model for multi-label choice problems
title_short The classifier chain generalized maximum entropy model for multi-label choice problems
title_full The classifier chain generalized maximum entropy model for multi-label choice problems
title_fullStr The classifier chain generalized maximum entropy model for multi-label choice problems
title_full_unstemmed The classifier chain generalized maximum entropy model for multi-label choice problems
title_sort classifier chain generalized maximum entropy model for multi-label choice problems
publisher Springer Verlag
publishDate 2015
url http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=84919344189&origin=inward
http://cmuir.cmu.ac.th/handle/6653943832/39142
_version_ 1681421600981778432