Predicting Out-of-Stock Using Machine Learning: An Application in a Retail Packaged Foods Manufacturing Company

For decades, Out-of-Stock (OOS) events have been a problem for retailers and manufacturers. In grocery retailing, an OOS event is used to characterize the condition in which customers do not find a certain commodity while attempting to buy it. This paper focuses on addressing this problem from a man...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Juan Manuel Rozas Andaur, Gonzalo A. Ruz, Marcos Goycoolea
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	out of stock machine learning classification algorithms imbalance data supply chain management decision support Electronics TK7800-8360
Acceso en línea:	https://doaj.org/article/6cb49aaca9b343dfab19bb79b7415530
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6cb49aaca9b343dfab19bb79b7415530
record_format	dspace
spelling	oai:doaj.org-article:6cb49aaca9b343dfab19bb79b74155302021-11-25T17:24:38ZPredicting Out-of-Stock Using Machine Learning: An Application in a Retail Packaged Foods Manufacturing Company10.3390/electronics102227872079-9292https://doaj.org/article/6cb49aaca9b343dfab19bb79b74155302021-11-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/22/2787https://doaj.org/toc/2079-9292For decades, Out-of-Stock (OOS) events have been a problem for retailers and manufacturers. In grocery retailing, an OOS event is used to characterize the condition in which customers do not find a certain commodity while attempting to buy it. This paper focuses on addressing this problem from a manufacturer’s perspective, conducting a case study in a retail packaged foods manufacturing company located in Latin America. We developed two machine learning based systems to detect OOS events automatically. The first is based on a single Random Forest classifier with balanced data, and the second is an ensemble of six different classification algorithms. We used transactional data from the manufacturer information system and physical audits. The novelty of this work is our use of new predictor variables of OOS events. The system was successfully implemented and tested in a retail packaged foods manufacturer company. By incorporating the new predictive variables in our Random Forest and Ensemble classifier, we were able to improve their system’s predictive power. In particular, the Random Forest classifier presented the best performance in a real-world setting, achieving a detection precision of 72% and identifying 68% of the total OOS events. Finally, the incorporation of our new predictor variables allowed us to improve the performance of the Random Forest by 0.24 points in the F-measure.Juan Manuel Rozas AndaurGonzalo A. RuzMarcos GoycooleaMDPI AGarticleout of stockmachine learningclassification algorithmsimbalance datasupply chain managementdecision supportElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2787, p 2787 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	out of stock machine learning classification algorithms imbalance data supply chain management decision support Electronics TK7800-8360
spellingShingle	out of stock machine learning classification algorithms imbalance data supply chain management decision support Electronics TK7800-8360 Juan Manuel Rozas Andaur Gonzalo A. Ruz Marcos Goycoolea Predicting Out-of-Stock Using Machine Learning: An Application in a Retail Packaged Foods Manufacturing Company
description	For decades, Out-of-Stock (OOS) events have been a problem for retailers and manufacturers. In grocery retailing, an OOS event is used to characterize the condition in which customers do not find a certain commodity while attempting to buy it. This paper focuses on addressing this problem from a manufacturer’s perspective, conducting a case study in a retail packaged foods manufacturing company located in Latin America. We developed two machine learning based systems to detect OOS events automatically. The first is based on a single Random Forest classifier with balanced data, and the second is an ensemble of six different classification algorithms. We used transactional data from the manufacturer information system and physical audits. The novelty of this work is our use of new predictor variables of OOS events. The system was successfully implemented and tested in a retail packaged foods manufacturer company. By incorporating the new predictive variables in our Random Forest and Ensemble classifier, we were able to improve their system’s predictive power. In particular, the Random Forest classifier presented the best performance in a real-world setting, achieving a detection precision of 72% and identifying 68% of the total OOS events. Finally, the incorporation of our new predictor variables allowed us to improve the performance of the Random Forest by 0.24 points in the F-measure.
format	article
author	Juan Manuel Rozas Andaur Gonzalo A. Ruz Marcos Goycoolea
author_facet	Juan Manuel Rozas Andaur Gonzalo A. Ruz Marcos Goycoolea
author_sort	Juan Manuel Rozas Andaur
title	Predicting Out-of-Stock Using Machine Learning: An Application in a Retail Packaged Foods Manufacturing Company
title_short	Predicting Out-of-Stock Using Machine Learning: An Application in a Retail Packaged Foods Manufacturing Company
title_full	Predicting Out-of-Stock Using Machine Learning: An Application in a Retail Packaged Foods Manufacturing Company
title_fullStr	Predicting Out-of-Stock Using Machine Learning: An Application in a Retail Packaged Foods Manufacturing Company
title_full_unstemmed	Predicting Out-of-Stock Using Machine Learning: An Application in a Retail Packaged Foods Manufacturing Company
title_sort	predicting out-of-stock using machine learning: an application in a retail packaged foods manufacturing company
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/6cb49aaca9b343dfab19bb79b7415530
work_keys_str_mv	AT juanmanuelrozasandaur predictingoutofstockusingmachinelearninganapplicationinaretailpackagedfoodsmanufacturingcompany AT gonzaloaruz predictingoutofstockusingmachinelearninganapplicationinaretailpackagedfoodsmanufacturingcompany AT marcosgoycoolea predictingoutofstockusingmachinelearninganapplicationinaretailpackagedfoodsmanufacturingcompany
_version_	1718412413042163712

Predicting Out-of-Stock Using Machine Learning: An Application in a Retail Packaged Foods Manufacturing Company

Ejemplares similares