An Explainable Machine Learning Model for Material Backorder Prediction in Inventory Management

Ntakolia, Charis; Kokkotis, Christos; Karlsson, Patrik; Moustakidis, Serafeim

doi:10.3390/s21237926

Cited by 19 publications

(16 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As we have found the study made by Ntakolia et al[10] made better accuracy and roc-auc score than the previous ones, so we made a further comparison of hyperparameters used in the study of Ntakolia et al and our study.…”

mentioning

confidence: 68%

A Comparative Analysis Of Machine Learning Algorithms To Predict Backorder In Supply Chain Management

Banik,

Islam,

Rahman

et al. 2023

Preprint

View full text Add to dashboard Cite

In supply chain inventory management, the backorder of products is a common occurrence. A backorder can only be successful if the supplier can be relied upon to provide the out-of-stock product when required or if the consumer is prepared to wait for the product without becoming impatient. So, to avoid uncertain circumstances and lessen the loss, it is important to know which goods are more likely to be back-ordered ahead of time so that appropriate measures can be taken. This work presents a backorder predictive model based on an imbalanced historical dataset obtained from an online source. The data has undergone sampling techniques, various Machine Learning algorithms, and evaluation metrics. After Random Undersampling (RUS), Random Forest (RF) achieved the highest accuracy of 99.328% while an accuracy of 98.917% was obtained from Extreme Gradient Boosting (XGBoost) model, which was highest after applying Synthetic Minority Oversampling Technique (SMOTE). XGBoost has outperformed other models with highest ROC-AUC score of 94.55% and 95.93% for oversampled and undersampled data respectively. In this paper, we made a visualization of the attributes of the dataset, then applied and analyzed Machine Learning algorithms to predict the backorder.

show abstract

mentioning

confidence: 68%

A Comparative Analysis Of Machine Learning Algorithms To Predict Backorder In Supply Chain Management

Banik,

Islam,

Rahman

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The LGBM machine learning algorithm was chosen to classify LUAD and LUSC patients from normal samples, consistently outperforming similar machine learning algoritms [ 38 , 39 ]. The classifier was implemented using official python packages from Microsoft.…”

Section: Methodsmentioning

confidence: 99%

Archaea Microbiome Dysregulated Genes and Pathways as Molecular Targets for Lung Adenocarcinoma and Squamous Cell Carcinoma

Uzelac

Chakladar

et al. 2022

IJMS

View full text Add to dashboard Cite

The human microbiome is a vast collection of microbial species that exist throughout the human body and regulate various bodily functions and phenomena. Of the microbial species that exist in the human microbiome, those within the archaea domain have not been characterized to the extent of those in more common domains, despite their potential for unique metabolic interaction with host cells. Research has correlated tumoral presence of bacterial microbial species to the development and progression of lung cancer; however, the impacts and influences of archaea in the microbiome remain heavily unexplored. Within the United States lung cancer remains highly fatal, responsible for over 100,000 deaths every year with a 5-year survival rate of roughly 22.9%. This project attempts to investigate specific archaeal species’ correlation to lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC) incidence, patient staging, death rates across individuals of varying ages, races, genders, and smoking-statuses, and potential molecular targets associated with archaea microbiome. Archaeal species abundance was assessed across lung tissue samples of 527 LUAD patients, 479 LUSC patients, and 99 healthy individuals. Nine archaeal species were found to be of significantly altered abundance in cancerous samples as compared to normal counterparts, 6 of which are common to both LUAD and LUSC subgroups. Several of these species are of the taxonomic class Thermoprotei or the phylum Euryarchaeota, both known to contain metabolic processes distinct from most bacterial species. Host-microbe metabolic interactions may be responsible for the observed correlation of these species’ abundance with cancer incidence. Significant microbes were correlated to patient gene expression to reveal genes of altered abundance with respect to high and low archaeal presence. With these genes, cellular oncogenic signaling pathways were analyzed for enrichment across cancer and normal samples. In comparing gene expression between LUAD and adjacent normal samples, 2 gene sets were found to be significantly enriched in cancers. In LUSC comparison, 6 sets were significantly enriched in cancer, and 34 were enriched in normals. Microbial counts across healthy and cancerous patients were then used to develop a machine-learning based predictive algorithm, capable of distinguishing lung cancer patients from healthy normal with 99% accuracy.

show abstract

“…ML algorithms can predict future demand based on historical data, market trends, and other relevant factors. By accurately forecasting demand, companies can optimize their inventory levels to meet customer demand while minimizing excess inventory (Ntakolia, et. al., 2021, Tadayonrad & Ndiaye, 2023, Zohra Benhamida, et.…”

Section: In Inventory Managementmentioning

confidence: 99%

Machine Learning's Influence on Supply Chain and Logistics Optimization in the Oil and Gas Sector: A Comprehensive Analysis

Agnes Clare Odimarha,

Sodrudeen Abolore Ayodeji,

Emmanuel Adeyemi Abaku

2024

Comput. sci. IT res. j.

View full text Add to dashboard Cite

Machine Learning (ML) is revolutionizing supply chain and logistics optimization in the oil and gas sector. This comprehensive analysis explores how ML algorithms are reshaping traditional practices, leading to more efficient operations and cost savings. ML enables predictive analytics, demand forecasting, route optimization, and inventory management, improving overall supply chain performance. Supply chain and logistics in the oil and gas sector are inherently complex, involving numerous interconnected processes and stakeholders. ML algorithms are adept at handling this complexity by analyzing vast amounts of data to identify patterns and optimize operations. By leveraging historical data, ML can predict future demand, enabling companies to adjust their inventory levels and production schedules accordingly. ML algorithms also play a crucial role in route optimization, helping companies minimize transportation costs and reduce carbon emissions. By analyzing factors such as traffic patterns, weather conditions, and road conditions, ML algorithms can determine the most efficient routes for transporting goods and equipment. Furthermore, ML enables predictive maintenance, which is essential in the oil and gas sector to prevent equipment failures and downtime. By analyzing sensor data from equipment, ML algorithms can predict when maintenance is required, allowing companies to schedule maintenance proactively and avoid costly disruptions. In conclusion, ML is transforming supply chain and logistics optimization in the oil and gas sector by enabling predictive analytics, demand forecasting, route optimization, and predictive maintenance. By leveraging the power of ML, companies in the oil and gas sector can improve operational efficiency, reduce costs, and enhance overall supply chain performance. Keywords: Machine’s Learning, Supply Chain, Logistics, Optimization, Oil and Gas.

show abstract

An Explainable Machine Learning Model for Material Backorder Prediction in Inventory Management

Cited by 19 publications

References 47 publications

A Comparative Analysis Of Machine Learning Algorithms To Predict Backorder In Supply Chain Management

A Comparative Analysis Of Machine Learning Algorithms To Predict Backorder In Supply Chain Management

Archaea Microbiome Dysregulated Genes and Pathways as Molecular Targets for Lung Adenocarcinoma and Squamous Cell Carcinoma

Machine Learning's Influence on Supply Chain and Logistics Optimization in the Oil and Gas Sector: A Comprehensive Analysis

Contact Info

Product

Resources

About