國立虎尾科技大學 |

Machine Learning in Automating Supply Management Maturity Ratings.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Machine Learning in Automating Supply Management Maturity Ratings./
Author:	Huang, Yung-Yun.
Description:	1 online resource (173 pages)
Notes:	Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
Contained By:	Dissertation Abstracts International78-10B(E).
Subject:	Operations research. -
Online resource:	click for full text (PQDT)
ISBN:	9781369856194

Machine Learning in Automating Supply Management Maturity Ratings.
Huang, Yung-Yun.

Machine Learning in Automating Supply Management Maturity Ratings. - 1 online resource (173 pages)

Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.

Thesis (Ph.D.)

Includes bibliographical references

Automating processes have the potential to significantly improve current methodologies for generating maturity ratings to evaluate supply management performance across diverse companies. We developed and applied a rigorous automation process to assess the supply management maturity ratings of over 600 global companies. To do this, we compared unigram and bigram feature settings, three text summarization techniques (full text, paragraph extraction and sentence extraction), and two different support vector machine approaches (oneagainst- one and one-against-all) on balanced and imbalanced datasets. Our automation process exhibits an 89.9% accuracy to the manually acquired maturity ratings. Further, we show that sentence extraction coupled with bigram feature settings produce the best model accuracy compare to all other combinations of feature settings. We show that class imbalance is a major cause of reduced machine learning algorithms (logistic regression and support vector machines) effectiveness, and therefore, remedy approaches should be used to ensure best performance. Our developed automation process could be adapted as an external evaluation approach (through public online resources) to assess supply chain sustainability maturity, such as labor & human rights and environmental management.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781369856194Subjects--Topical Terms:

573517
Operations research.
Index Terms--Genre/Form:

554714
Electronic books.

Machine Learning in Automating Supply Management Maturity Ratings.
LDR:02564ntm a2200337Ki 4500 001 910805
005 20180517112611.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9781369856194
035 $a (MiAaPQ)AAI10610736
035 $a AAI10610736
040 $a MiAaPQ $b eng $c MiAaPQ
099 $a TUL $f hyy $c available through World Wide Web
100 1 $a Huang, Yung-Yun. $3 1182268
245 1 0 $a Machine Learning in Automating Supply Management Maturity Ratings.
264 0 $c 2017
300 $a 1 online resource (173 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
500 $a Adviser: Robert B. Handfield.
502 $a Thesis (Ph.D.) $c North Carolina State University $d 2017.
504 $a Includes bibliographical references
520 $a Automating processes have the potential to significantly improve current methodologies for generating maturity ratings to evaluate supply management performance across diverse companies. We developed and applied a rigorous automation process to assess the supply management maturity ratings of over 600 global companies. To do this, we compared unigram and bigram feature settings, three text summarization techniques (full text, paragraph extraction and sentence extraction), and two different support vector machine approaches (oneagainst- one and one-against-all) on balanced and imbalanced datasets. Our automation process exhibits an 89.9% accuracy to the manually acquired maturity ratings. Further, we show that sentence extraction coupled with bigram feature settings produce the best model accuracy compare to all other combinations of feature settings. We show that class imbalance is a major cause of reduced machine learning algorithms (logistic regression and support vector machines) effectiveness, and therefore, remedy approaches should be used to ensure best performance. Our developed automation process could be adapted as an external evaluation approach (through public online resources) to assess supply chain sustainability maturity, such as labor & human rights and environmental management.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Operations research. $3 573517
650 4 $a Artificial intelligence. $3 559380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0796
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a North Carolina State University. $b Operations Research. $3 1182269
773 0 $t Dissertation Abstracts International $g 78-10B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10610736 $z click for full text (PQDT)