No Cover Image

Journal article 584 views

Product backorder prediction using deep neural network on imbalanced data

Md Shajalal, Petr Hajek, Mohammad Abedin Orcid Logo

International Journal of Production Research, Volume: 61, Issue: 1, Pages: 302 - 319

Swansea University Author: Mohammad Abedin Orcid Logo

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.1080/00207543.2021.1901153

Abstract

Taking backorders on products is a common scenario in inventory and supply chain management systems. The ability to predict the likelihood of backorders can surely minimise a company's losses. Because the number of backorders is much lower than the number of orders that ship on time, applying a...

Full description

Published in: International Journal of Production Research
ISSN: 0020-7543 1366-588X
Published: Informa UK Limited 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa64236
first_indexed 2023-09-19T14:58:38Z
last_indexed 2024-11-25T14:13:41Z
id cronfa64236
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2023-09-19T15:58:35.1553502</datestamp><bib-version>v2</bib-version><id>64236</id><entry>2023-08-31</entry><title>Product backorder prediction using deep neural network on imbalanced data</title><swanseaauthors><author><sid>4ed8c020eae0c9bec4f5d9495d86d415</sid><ORCID>0000-0002-4688-0619</ORCID><firstname>Mohammad</firstname><surname>Abedin</surname><name>Mohammad Abedin</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-08-31</date><deptcode>CBAE</deptcode><abstract>Taking backorders on products is a common scenario in inventory and supply chain management systems. The ability to predict the likelihood of backorders can surely minimise a company's losses. Because the number of backorders is much lower than the number of orders that ship on time, applying a predictive model for this domain is a challenging task. This paper proposes a model that uses a deep neural network to predict backorders; it handles the data imbalance between backorders and filled orders with efficient techniques. To make the dataset balanced, we employ different techniques that include minority class weight boosting, randomised oversampling, SMOTE oversampling, and a combination of oversampling and undersampling. The balanced training data are used in our proposed, fully connected deep neural networks model to train the predictive model. The predictive model learns the likelihood of product backorders by using the training samples. We conduct experiments on a large benchmark dataset to test the performance of our proposed deep neural network&#x2013;based model. The experimental results achieve a new state-of-the-art performance and outperform some prominent classification models in terms of standard evaluation metrics and expected profit measure.</abstract><type>Journal Article</type><journal>International Journal of Production Research</journal><volume>61</volume><journalNumber>1</journalNumber><paginationStart>302</paginationStart><paginationEnd>319</paginationEnd><publisher>Informa UK Limited</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0020-7543</issnPrint><issnElectronic>1366-588X</issnElectronic><keywords>Product backorder, deep neural network, synthetic oversampling, imbalanced data, prediction</keywords><publishedDay>2</publishedDay><publishedMonth>1</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-01-02</publishedDate><doi>10.1080/00207543.2021.1901153</doi><url>http://dx.doi.org/10.1080/00207543.2021.1901153</url><notes/><college>COLLEGE NANME</college><department>Management School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>CBAE</DepartmentCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2023-09-19T15:58:35.1553502</lastEdited><Created>2023-08-31T17:37:47.0757727</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>Md</firstname><surname>Shajalal</surname><order>1</order></author><author><firstname>Petr</firstname><surname>Hajek</surname><order>2</order></author><author><firstname>Mohammad</firstname><surname>Abedin</surname><orcid>0000-0002-4688-0619</orcid><order>3</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2023-09-19T15:58:35.1553502 v2 64236 2023-08-31 Product backorder prediction using deep neural network on imbalanced data 4ed8c020eae0c9bec4f5d9495d86d415 0000-0002-4688-0619 Mohammad Abedin Mohammad Abedin true false 2023-08-31 CBAE Taking backorders on products is a common scenario in inventory and supply chain management systems. The ability to predict the likelihood of backorders can surely minimise a company's losses. Because the number of backorders is much lower than the number of orders that ship on time, applying a predictive model for this domain is a challenging task. This paper proposes a model that uses a deep neural network to predict backorders; it handles the data imbalance between backorders and filled orders with efficient techniques. To make the dataset balanced, we employ different techniques that include minority class weight boosting, randomised oversampling, SMOTE oversampling, and a combination of oversampling and undersampling. The balanced training data are used in our proposed, fully connected deep neural networks model to train the predictive model. The predictive model learns the likelihood of product backorders by using the training samples. We conduct experiments on a large benchmark dataset to test the performance of our proposed deep neural network–based model. The experimental results achieve a new state-of-the-art performance and outperform some prominent classification models in terms of standard evaluation metrics and expected profit measure. Journal Article International Journal of Production Research 61 1 302 319 Informa UK Limited 0020-7543 1366-588X Product backorder, deep neural network, synthetic oversampling, imbalanced data, prediction 2 1 2023 2023-01-02 10.1080/00207543.2021.1901153 http://dx.doi.org/10.1080/00207543.2021.1901153 COLLEGE NANME Management School COLLEGE CODE CBAE Swansea University 2023-09-19T15:58:35.1553502 2023-08-31T17:37:47.0757727 Faculty of Humanities and Social Sciences School of Management - Accounting and Finance Md Shajalal 1 Petr Hajek 2 Mohammad Abedin 0000-0002-4688-0619 3
title Product backorder prediction using deep neural network on imbalanced data
spellingShingle Product backorder prediction using deep neural network on imbalanced data
Mohammad Abedin
title_short Product backorder prediction using deep neural network on imbalanced data
title_full Product backorder prediction using deep neural network on imbalanced data
title_fullStr Product backorder prediction using deep neural network on imbalanced data
title_full_unstemmed Product backorder prediction using deep neural network on imbalanced data
title_sort Product backorder prediction using deep neural network on imbalanced data
author_id_str_mv 4ed8c020eae0c9bec4f5d9495d86d415
author_id_fullname_str_mv 4ed8c020eae0c9bec4f5d9495d86d415_***_Mohammad Abedin
author Mohammad Abedin
author2 Md Shajalal
Petr Hajek
Mohammad Abedin
format Journal article
container_title International Journal of Production Research
container_volume 61
container_issue 1
container_start_page 302
publishDate 2023
institution Swansea University
issn 0020-7543
1366-588X
doi_str_mv 10.1080/00207543.2021.1901153
publisher Informa UK Limited
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
url http://dx.doi.org/10.1080/00207543.2021.1901153
document_store_str 0
active_str 0
description Taking backorders on products is a common scenario in inventory and supply chain management systems. The ability to predict the likelihood of backorders can surely minimise a company's losses. Because the number of backorders is much lower than the number of orders that ship on time, applying a predictive model for this domain is a challenging task. This paper proposes a model that uses a deep neural network to predict backorders; it handles the data imbalance between backorders and filled orders with efficient techniques. To make the dataset balanced, we employ different techniques that include minority class weight boosting, randomised oversampling, SMOTE oversampling, and a combination of oversampling and undersampling. The balanced training data are used in our proposed, fully connected deep neural networks model to train the predictive model. The predictive model learns the likelihood of product backorders by using the training samples. We conduct experiments on a large benchmark dataset to test the performance of our proposed deep neural network–based model. The experimental results achieve a new state-of-the-art performance and outperform some prominent classification models in terms of standard evaluation metrics and expected profit measure.
published_date 2023-01-02T05:28:25Z
_version_ 1821382075647787008
score 11.29607

Similar Items