Abstract:
Manufacturing is changing quickly in parallel with market trends. Precise forecasting is critical for suppliers, impacting the worldwide supply chain network-a range of p...Show MoreMetadata
Abstract:
Manufacturing is changing quickly in parallel with market trends. Precise forecasting is critical for suppliers, impacting the worldwide supply chain network-a range of products derived from various sources and places in manufacturing plants in inbound logistics. Planning these inbound logistics depends on inventory readiness, plant planning, sourcing, and knowledge (continuously evolving). This paper focuses on machine learning algorithms such as K-nearest neighbors (KNN), Random Forests, Support Vector Machine (SVM) to improve the planning of inbound logistics systems. The presented algorithms track and train consumer preferences, policies, and other complex planning considerations in the planning process, such as time, strategy, and network design. In the planning process, half the time is spent preparing and collecting data, while the gained experience is not utilized efficiently. Therefore, designing potential inbound logistics processes are addressed using machine learning algorithms such as KNN, random forests, and SVM.
Date of Conference: 27-30 January 2021
Date Added to IEEE Xplore: 17 March 2021
ISBN Information: