Skip to content
Back to outputs

Machine learning for multi-criteria inventory classification applied to intermittent demand

Research output: Contribution to journalArticle

Standard

Machine learning for multi-criteria inventory classification applied to intermittent demand. / Lolli, Francesco; Balugani, Elia ; Ishizaka, Alessio; Gamberini, Rita; Rimini, Bianca; Alberto, Regattieri.

In: Production Planning and Control, 31.10.2018.

Research output: Contribution to journalArticle

Harvard

Lolli, F, Balugani, E, Ishizaka, A, Gamberini, R, Rimini, B & Alberto, R 2018, 'Machine learning for multi-criteria inventory classification applied to intermittent demand', Production Planning and Control. https://doi.org/10.1080/09537287.2018.1525506

APA

Lolli, F., Balugani, E., Ishizaka, A., Gamberini, R., Rimini, B., & Alberto, R. (2018). Machine learning for multi-criteria inventory classification applied to intermittent demand. Production Planning and Control. https://doi.org/10.1080/09537287.2018.1525506

Vancouver

Lolli F, Balugani E, Ishizaka A, Gamberini R, Rimini B, Alberto R. Machine learning for multi-criteria inventory classification applied to intermittent demand. Production Planning and Control. 2018 Oct 31. https://doi.org/10.1080/09537287.2018.1525506

Author

Lolli, Francesco ; Balugani, Elia ; Ishizaka, Alessio ; Gamberini, Rita ; Rimini, Bianca ; Alberto, Regattieri. / Machine learning for multi-criteria inventory classification applied to intermittent demand. In: Production Planning and Control. 2018.

Bibtex

@article{c6aeb1f5f4124758aa32c12131b5445f,
title = "Machine learning for multi-criteria inventory classification applied to intermittent demand",
abstract = "Multi-criteria inventory classification groups inventory items into classes, each of which is managed by a specific re-order policy according to its priority. However, the tasks of inventory classification and control are not carried out jointly if the classification criteria and the classification approach are not robustly established from an inventory-cost perspective. Exhaustive simulations at the single item level of the inventory system would directly solve this issue by searching for the best re-order policy per item, thus achieving the subsequent optimal classification without resorting to any multi-criteria classification method. However, this would be very time-consuming in real settings, where a large number of items need to be managed simultaneously.In this article, a reduction in simulation effort is achieved by extracting from the population of items a sample on which to perform an exhaustive search of best re-order policies per item; the lowest cost classification of in-sample items is, therefore, achieved. Then, in line with the increasing need for ICT tools in the production management of Industry 4.0 systems, supervised classifiers from the machine learning research field (i.e. support vector machines with a Gaussian kernel and deep neural networks) are trained on these in-sample items to learn to classify the out-of-sample items solely based on the values they show on the features (i.e. classification criteria). The inventory system adopted here is suitable for intermittent demands, but it may also suit non-intermittent demands, thus providing great flexibility. The experimental analysis of two large datasets showed an excellent accuracy, which suggests that machine learning classifiers could be implemented in advanced inventory classification systems.",
keywords = "Multi-criteria inventory classification, Inventory control, Industry 4.0, Machine learning, Intermittent demand",
author = "Francesco Lolli and Elia Balugani and Alessio Ishizaka and Rita Gamberini and Bianca Rimini and Regattieri Alberto",
year = "2018",
month = oct,
day = "31",
doi = "10.1080/09537287.2018.1525506",
language = "English",
journal = "Production Planning and Control",
issn = "0953-7287",
publisher = "Taylor & Francis",

}

RIS

TY - JOUR

T1 - Machine learning for multi-criteria inventory classification applied to intermittent demand

AU - Lolli, Francesco

AU - Balugani, Elia

AU - Ishizaka, Alessio

AU - Gamberini, Rita

AU - Rimini, Bianca

AU - Alberto, Regattieri

PY - 2018/10/31

Y1 - 2018/10/31

N2 - Multi-criteria inventory classification groups inventory items into classes, each of which is managed by a specific re-order policy according to its priority. However, the tasks of inventory classification and control are not carried out jointly if the classification criteria and the classification approach are not robustly established from an inventory-cost perspective. Exhaustive simulations at the single item level of the inventory system would directly solve this issue by searching for the best re-order policy per item, thus achieving the subsequent optimal classification without resorting to any multi-criteria classification method. However, this would be very time-consuming in real settings, where a large number of items need to be managed simultaneously.In this article, a reduction in simulation effort is achieved by extracting from the population of items a sample on which to perform an exhaustive search of best re-order policies per item; the lowest cost classification of in-sample items is, therefore, achieved. Then, in line with the increasing need for ICT tools in the production management of Industry 4.0 systems, supervised classifiers from the machine learning research field (i.e. support vector machines with a Gaussian kernel and deep neural networks) are trained on these in-sample items to learn to classify the out-of-sample items solely based on the values they show on the features (i.e. classification criteria). The inventory system adopted here is suitable for intermittent demands, but it may also suit non-intermittent demands, thus providing great flexibility. The experimental analysis of two large datasets showed an excellent accuracy, which suggests that machine learning classifiers could be implemented in advanced inventory classification systems.

AB - Multi-criteria inventory classification groups inventory items into classes, each of which is managed by a specific re-order policy according to its priority. However, the tasks of inventory classification and control are not carried out jointly if the classification criteria and the classification approach are not robustly established from an inventory-cost perspective. Exhaustive simulations at the single item level of the inventory system would directly solve this issue by searching for the best re-order policy per item, thus achieving the subsequent optimal classification without resorting to any multi-criteria classification method. However, this would be very time-consuming in real settings, where a large number of items need to be managed simultaneously.In this article, a reduction in simulation effort is achieved by extracting from the population of items a sample on which to perform an exhaustive search of best re-order policies per item; the lowest cost classification of in-sample items is, therefore, achieved. Then, in line with the increasing need for ICT tools in the production management of Industry 4.0 systems, supervised classifiers from the machine learning research field (i.e. support vector machines with a Gaussian kernel and deep neural networks) are trained on these in-sample items to learn to classify the out-of-sample items solely based on the values they show on the features (i.e. classification criteria). The inventory system adopted here is suitable for intermittent demands, but it may also suit non-intermittent demands, thus providing great flexibility. The experimental analysis of two large datasets showed an excellent accuracy, which suggests that machine learning classifiers could be implemented in advanced inventory classification systems.

KW - Multi-criteria inventory classification

KW - Inventory control

KW - Industry 4.0

KW - Machine learning

KW - Intermittent demand

U2 - 10.1080/09537287.2018.1525506

DO - 10.1080/09537287.2018.1525506

M3 - Article

JO - Production Planning and Control

JF - Production Planning and Control

SN - 0953-7287

ER -

ID: 11685436