No Cover Image

Journal article 321 views 55 downloads

Predicting the performance of MSMEs: a hybrid DEA-machine learning approach

Sabri Boubaker Orcid Logo, Tu D. Q. Le, Thanh Ngo Orcid Logo, Riadh Manita

Annals of Operations Research, Volume: 350, Issue: 2, Pages: 555 - 577

Swansea University Author: Sabri Boubaker Orcid Logo

  • 10479_2023_Article_5230.pdf

    PDF | Version of Record

    © The Author(s) 2023. This article is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).

    Download (539.58KB)

Check full text

DOI (Published version): 10.1007/s10479-023-05230-8

Abstract

Micro, small and medium enterprises (MSMEs) dominate the business landscape and create more than half of employment worldwide. How we can apply big data analytical tools such as machine learning to examine the performance of MSMEs has become an important question to provide quicker results and recom...

Full description

Published in: Annals of Operations Research
ISSN: 0254-5330 1572-9338
Published: Springer Nature 2025
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa70080
first_indexed 2025-07-31T12:45:59Z
last_indexed 2025-08-01T14:34:01Z
id cronfa70080
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-07-31T13:47:17.3491175</datestamp><bib-version>v2</bib-version><id>70080</id><entry>2025-07-31</entry><title>Predicting the performance of MSMEs: a hybrid DEA-machine learning approach</title><swanseaauthors><author><sid>43999fff86cd8a29f4815fb4dfa47729</sid><ORCID>0000-0002-6416-2952</ORCID><firstname>Sabri</firstname><surname>Boubaker</surname><name>Sabri Boubaker</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-07-31</date><deptcode>CBAE</deptcode><abstract>Micro, small and medium enterprises (MSMEs) dominate the business landscape and create more than half of employment worldwide. How we can apply big data analytical tools such as machine learning to examine the performance of MSMEs has become an important question to provide quicker results and recommend better and more reliable solutions that improve performance. This paper proposes a novel method for estimating a common set of weights (CSW) based on regression analysis for data envelopment analysis (DEA) as an important analytical and operational research technique, which (i) allows for measurement evaluations and ranking comparisons of the MSMEs, and (ii) helps overcome the time-consuming non-convexity issues of other CSW DEA methodologies. Our hybrid approach used several econometric and machine learning techniques (such as Tobit, least absolute shrinkage and selection operator, and Random Forest regression) to empirically explain and predict the performance of more than 5400 Vietnamese MSMEs (2010&#x2012;2016), and showed that the machine learning techniques are more efficient and accurate than the econometric ones. Our study, therefore, sheds new light on the two-stage DEA literature, especially in terms of predicting performance in the era of big data to strengthen the role of analytics in business and management.</abstract><type>Journal Article</type><journal>Annals of Operations Research</journal><volume>350</volume><journalNumber>2</journalNumber><paginationStart>555</paginationStart><paginationEnd>577</paginationEnd><publisher>Springer Nature</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0254-5330</issnPrint><issnElectronic>1572-9338</issnElectronic><keywords>Machine learning (ML); Common set of weights (CSW); Data envelopment analysis (DEA); Micro, small, and medium enterprise (MSME); Efficiency</keywords><publishedDay>1</publishedDay><publishedMonth>7</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-07-01</publishedDate><doi>10.1007/s10479-023-05230-8</doi><url/><notes/><college>COLLEGE NANME</college><department>Management School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>CBAE</DepartmentCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders>Open Access funding enabled and organized by CAUL and its Member Institutions.</funders><projectreference/><lastEdited>2025-07-31T13:47:17.3491175</lastEdited><Created>2025-07-31T13:39:15.2368394</Created><path><level id="1">Faculty of Humanities and Social Sciences</level><level id="2">School of Management - Accounting and Finance</level></path><authors><author><firstname>Sabri</firstname><surname>Boubaker</surname><orcid>0000-0002-6416-2952</orcid><order>1</order></author><author><firstname>Tu D. Q.</firstname><surname>Le</surname><order>2</order></author><author><firstname>Thanh</firstname><surname>Ngo</surname><orcid>0000-0002-6090-8067</orcid><order>3</order></author><author><firstname>Riadh</firstname><surname>Manita</surname><order>4</order></author></authors><documents><document><filename>70080__34892__6226aa3611544f1e9d2ac030c0da8fab.pdf</filename><originalFilename>10479_2023_Article_5230.pdf</originalFilename><uploaded>2025-07-31T13:39:15.2362864</uploaded><type>Output</type><contentLength>552525</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; The Author(s) 2023. This article is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2025-07-31T13:47:17.3491175 v2 70080 2025-07-31 Predicting the performance of MSMEs: a hybrid DEA-machine learning approach 43999fff86cd8a29f4815fb4dfa47729 0000-0002-6416-2952 Sabri Boubaker Sabri Boubaker true false 2025-07-31 CBAE Micro, small and medium enterprises (MSMEs) dominate the business landscape and create more than half of employment worldwide. How we can apply big data analytical tools such as machine learning to examine the performance of MSMEs has become an important question to provide quicker results and recommend better and more reliable solutions that improve performance. This paper proposes a novel method for estimating a common set of weights (CSW) based on regression analysis for data envelopment analysis (DEA) as an important analytical and operational research technique, which (i) allows for measurement evaluations and ranking comparisons of the MSMEs, and (ii) helps overcome the time-consuming non-convexity issues of other CSW DEA methodologies. Our hybrid approach used several econometric and machine learning techniques (such as Tobit, least absolute shrinkage and selection operator, and Random Forest regression) to empirically explain and predict the performance of more than 5400 Vietnamese MSMEs (2010‒2016), and showed that the machine learning techniques are more efficient and accurate than the econometric ones. Our study, therefore, sheds new light on the two-stage DEA literature, especially in terms of predicting performance in the era of big data to strengthen the role of analytics in business and management. Journal Article Annals of Operations Research 350 2 555 577 Springer Nature 0254-5330 1572-9338 Machine learning (ML); Common set of weights (CSW); Data envelopment analysis (DEA); Micro, small, and medium enterprise (MSME); Efficiency 1 7 2025 2025-07-01 10.1007/s10479-023-05230-8 COLLEGE NANME Management School COLLEGE CODE CBAE Swansea University Another institution paid the OA fee Open Access funding enabled and organized by CAUL and its Member Institutions. 2025-07-31T13:47:17.3491175 2025-07-31T13:39:15.2368394 Faculty of Humanities and Social Sciences School of Management - Accounting and Finance Sabri Boubaker 0000-0002-6416-2952 1 Tu D. Q. Le 2 Thanh Ngo 0000-0002-6090-8067 3 Riadh Manita 4 70080__34892__6226aa3611544f1e9d2ac030c0da8fab.pdf 10479_2023_Article_5230.pdf 2025-07-31T13:39:15.2362864 Output 552525 application/pdf Version of Record true © The Author(s) 2023. This article is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). true eng http://creativecommons.org/licenses/by/4.0/
title Predicting the performance of MSMEs: a hybrid DEA-machine learning approach
spellingShingle Predicting the performance of MSMEs: a hybrid DEA-machine learning approach
Sabri Boubaker
title_short Predicting the performance of MSMEs: a hybrid DEA-machine learning approach
title_full Predicting the performance of MSMEs: a hybrid DEA-machine learning approach
title_fullStr Predicting the performance of MSMEs: a hybrid DEA-machine learning approach
title_full_unstemmed Predicting the performance of MSMEs: a hybrid DEA-machine learning approach
title_sort Predicting the performance of MSMEs: a hybrid DEA-machine learning approach
author_id_str_mv 43999fff86cd8a29f4815fb4dfa47729
author_id_fullname_str_mv 43999fff86cd8a29f4815fb4dfa47729_***_Sabri Boubaker
author Sabri Boubaker
author2 Sabri Boubaker
Tu D. Q. Le
Thanh Ngo
Riadh Manita
format Journal article
container_title Annals of Operations Research
container_volume 350
container_issue 2
container_start_page 555
publishDate 2025
institution Swansea University
issn 0254-5330
1572-9338
doi_str_mv 10.1007/s10479-023-05230-8
publisher Springer Nature
college_str Faculty of Humanities and Social Sciences
hierarchytype
hierarchy_top_id facultyofhumanitiesandsocialsciences
hierarchy_top_title Faculty of Humanities and Social Sciences
hierarchy_parent_id facultyofhumanitiesandsocialsciences
hierarchy_parent_title Faculty of Humanities and Social Sciences
department_str School of Management - Accounting and Finance{{{_:::_}}}Faculty of Humanities and Social Sciences{{{_:::_}}}School of Management - Accounting and Finance
document_store_str 1
active_str 0
description Micro, small and medium enterprises (MSMEs) dominate the business landscape and create more than half of employment worldwide. How we can apply big data analytical tools such as machine learning to examine the performance of MSMEs has become an important question to provide quicker results and recommend better and more reliable solutions that improve performance. This paper proposes a novel method for estimating a common set of weights (CSW) based on regression analysis for data envelopment analysis (DEA) as an important analytical and operational research technique, which (i) allows for measurement evaluations and ranking comparisons of the MSMEs, and (ii) helps overcome the time-consuming non-convexity issues of other CSW DEA methodologies. Our hybrid approach used several econometric and machine learning techniques (such as Tobit, least absolute shrinkage and selection operator, and Random Forest regression) to empirically explain and predict the performance of more than 5400 Vietnamese MSMEs (2010‒2016), and showed that the machine learning techniques are more efficient and accurate than the econometric ones. Our study, therefore, sheds new light on the two-stage DEA literature, especially in terms of predicting performance in the era of big data to strengthen the role of analytics in business and management.
published_date 2025-07-01T05:29:54Z
_version_ 1851097974010019840
score 11.444314

Similar Items