article · International journal of engineering research in Africa
Accurate demand forecasting is vital for effective supply chain and company performance, enabling organisations to optimise resource allocation and fulfil customer orders on schedule. Conventional forecasting methods often struggle when customer orders change frequently. To address this issue, an Internet of Things based inventory management system was developed that integrates multiple linear regression with genetic algorithms. This hybrid approach aims to predict customer demand more closely and support smart inventory practices aligned with Industry 4.0 principles. The system was evaluated using operational data from a semiconductor company specialising in low-volume, high-mix contract manufacturing equipment and services integration. The resulting system demonstrates improved inventory productivity and operational efficiency while showing resilience against regular fluctuations in customer orders.
Manufacturing companies frequently struggle to align stock levels with unpredictable client orders, leading to delays and wasted resources. By combining predictive algorithms with connected inventory tracking, businesses can anticipate demand shifts more reliably. This helps industrial facilities maintain timely deliveries, reduce excess holding costs, and adapt to rapidly evolving customer requirements.
The system targets manufacturing and supply chain operators, particularly those dealing with low-volume, high-mix production environments such as contract semiconductor assembly. Based on testing with historical company data, the approach shows practical promise for smart warehouse and inventory software tools. Further development into a deployable software platform would require integrating the algorithms with live enterprise resource planning and factory floor sensors.
AI-generated from the published abstract. Always read the original work before citing.
The accuracy of demand forecasting has a significant impact on the supply chain system's performance, which in turn has a major effect on company performance. Accurate forecasting will allow the organization to make the best use of its resources. The synchronization of customer orders to support production is critical for on-time order fulfillment. However, In fact many organizations report that their forecasting method is not working as effectively as they had hoped because orders regularly alter due to client demands. The purpose of this paper is to present an Internet of Things (IoT)-based inventory management system (IMS) that combines a causal method of multiple linear regressions (MLR) with genetic algorithms (GA) to improve the accuracy of demand forecasting in the future period by the customer as closely as feasible and enable smart inventory for Industry 4.0. Based on the data gathered from a semiconductor company that specializes in low-volume, high-mix contract manufacturing equipment and services integration, the suggested IoT-based IMS indicates that inventory productivity and efficiency could be enhanced, and it is resilient to order fluctuation.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.4028/p-8ntq24
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.
