article · Ain Shams Engineering Journal
Disruptions in material supply chains frequently harm planned production schedules, resulting in notable financial and operational consequences. Strengthening resilience remains difficult, particularly because firm-level logistics processes and mitigation strategies are rarely explored in detail. Focusing on the textile industry, this work investigates the application of data analytics and machine learning classifiers to predict supply chain disruptions. The approach uses an investigational design to assess feature selection spaces, evaluate the most effective algorithms, and establish a performance metric aligned with case study objectives. The investigation highlights the critical importance of domain knowledge when engineering features from operational supply chain data. Ultimately, the findings demonstrate that machine learning models can be effectively deployed to forecast disruptions in the textile sector and potentially across other industrial supply networks.
Supply chain disruptions regularly derail production timelines, leading to significant economic losses for manufacturing firms. Demonstrating how machine learning can forecast these breakdowns helps industrial organisations move from reactive problem-solving to proactive risk management. Highlighting domain-specific feature engineering provides a practical path for enterprises seeking to extract actionable predictive value from their internal logistics data.
The work could enable predictive risk-monitoring software for supply chain and operations managers in the textile sector and other manufacturing industries. Given that the abstract describes an investigational case study assessing feature spaces and algorithm performance, the technology appears to be at an applied research stage rather than near-market, requiring further software engineering and data integration before commercial deployment.
AI-generated from the published abstract. Always read the original work before citing.
The disruption of the material supply chain may impact planned production schedules with both, financial and non-financial implications. It has always been difficult to make the Supply Chain (SC) more resilient. There is a lack in the literature to examine how logistics processes operate at the firm level and the ways that can mitigate Supply Chain Disruptions (SCD). This work is focused on the textile industry as a case to explain the application of data analytics such as the ML model for predicting SCD. To conclude, the performance of each classifier is analyzed, to understand whether or not this approach applies to the selected problem. Creating effectiveness of the methods, a performance metric that correlates with the set objectives of the case study is developed. The work adopts an investigational design to identify the FS space and selectively review the most successful algorithms. This case study is important to a paper in the sense that it avails and demonstrates the use and development of data analytics techniques to work with SC data. The work is centered around stressing the importance of the notion of a domain when engineering features. Altogether, the paper contributes to expounding the possibility of employing different ML techniques for the estimation of SCD in the textile industry and other sectors.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.asej.2024.103116
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
